Add MLX-bf16 (weights + SEO card)
Browse files- .gitattributes +1 -0
- README.md +142 -0
- chat_template.jinja +352 -0
- config.json +155 -0
- generation_config.json +14 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +673 -0
- tokenizer.json +3 -0
- tokenizer_config.json +97 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
license_link: https://ai.google.dev/gemma/terms
|
| 4 |
+
library_name: mlx
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
base_model: Jiunsong/supergemma4-e4b-abliterated
|
| 7 |
+
base_model_relation: quantized
|
| 8 |
+
language:
|
| 9 |
+
- en
|
| 10 |
+
- ko
|
| 11 |
+
tags:
|
| 12 |
+
- gemma
|
| 13 |
+
- gemma-4
|
| 14 |
+
- gemma4
|
| 15 |
+
- abliterated
|
| 16 |
+
- uncensored
|
| 17 |
+
- uncensored-llm
|
| 18 |
+
- no-refusal
|
| 19 |
+
- mlx
|
| 20 |
+
- apple-silicon
|
| 21 |
+
- m-series
|
| 22 |
+
- mac
|
| 23 |
+
- quantized
|
| 24 |
+
- conversational
|
| 25 |
+
- roleplay
|
| 26 |
+
- text-generation
|
| 27 |
+
quantized_by: dancinlab
|
| 28 |
+
inference: false
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
+
# Uncensored Gemma 4 (SuperGemma4 E4B Abliterated) — MLX for Apple Silicon
|
| 32 |
+
|
| 33 |
+
**Uncensored / abliterated Gemma-4** for Apple Silicon — MLX builds that
|
| 34 |
+
**actually load on stock `mlx-lm`**. Most community MLX uploads of this base
|
| 35 |
+
fail with `Missing 963 parameters`; this repo's conversion fixes both root
|
| 36 |
+
causes so it loads and generates on a clean `pip install mlx-lm`.
|
| 37 |
+
|
| 38 |
+
```bash
|
| 39 |
+
pip install -U mlx-lm # needs mlx-lm >= 0.31.3 (native gemma4 arch)
|
| 40 |
+
|
| 41 |
+
# 4-bit — recommended for 16 GB / 24 GB Macs
|
| 42 |
+
mlx_lm.generate --model dancinlab/supergemma4-e4b-abliterated-MLX-bf16 \
|
| 43 |
+
--prompt "안녕? 너는 누구야?" --max-tokens 60
|
| 44 |
+
|
| 45 |
+
# interactive chat
|
| 46 |
+
mlx_lm.chat --model dancinlab/supergemma4-e4b-abliterated-MLX-bf16
|
| 47 |
+
```
|
| 48 |
+
|
| 49 |
+
## Builds (3 separate repos)
|
| 50 |
+
|
| 51 |
+
| Repo | Size | Peak RAM | tok/s (M-series) | Use |
|
| 52 |
+
|---|---:|---:|---:|---|
|
| 53 |
+
| **`-MLX-4bit`** | 3.9 GB | 5.4 GB | ~11 | **recommended** — 16 GB / 24 GB Mac |
|
| 54 |
+
| `-MLX-8bit` | 7.4 GB | 9.1 GB | ~6 | 32 GB+ Mac, higher fidelity |
|
| 55 |
+
| `-MLX-bf16` | 14 GB | 8.6 GB | ~3 | reference, full precision |
|
| 56 |
+
|
| 57 |
+
Verified: both `안녕? 너는 누구야?` (coherent Korean) and `2+2=` (→ 4) on
|
| 58 |
+
stock `mlx-lm==0.31.3`. **Text-only** — the upstream abliterated safetensors
|
| 59 |
+
contain no vision/audio tower weights, so multimodal MLX is upstream-blocked,
|
| 60 |
+
not a tooling limitation.
|
| 61 |
+
|
| 62 |
+
## Why community MLX builds fail (and how this one is fixed)
|
| 63 |
+
|
| 64 |
+
`Gemma4ForConditionalGeneration` is multimodal (text + vision + audio). Two
|
| 65 |
+
independent problems break naive conversion:
|
| 66 |
+
|
| 67 |
+
1. **963-tensor multimodal/text mismatch.** `mlx-vlm` always instantiates all
|
| 68 |
+
three towers (1682 tensors); the abliterated text-only release has 719
|
| 69 |
+
(missing = audio 751 + vision 210 + embed 2). **Fixed by stock code** —
|
| 70 |
+
`mlx-lm >= 0.31.3` ships a native `gemma4`/`gemma4_text` arch whose
|
| 71 |
+
`sanitize` strips vision/audio/embed and remaps `model.language_model.*`.
|
| 72 |
+
No patch needed for this part.
|
| 73 |
+
|
| 74 |
+
2. **54-tensor KV-shared residue.** Gemma-4 e4b shares K/V across the last 18
|
| 75 |
+
layers (24–41), but the upstream safetensors physically still carry the
|
| 76 |
+
dropped `k_proj`/`v_proj`/`k_norm` for those layers → strict-load failure.
|
| 77 |
+
This fix landed on `mlx-lm` `main` **after** the 0.31.3 tag
|
| 78 |
+
(`ml-explore/mlx-lm#1240`), so it is **not in any pip release yet**. This
|
| 79 |
+
repo applies the #1240 `sanitize` logic as a **convert-time monkey-patch**
|
| 80 |
+
(no mlx-lm / mlx-vlm / transformers fork). Effect: 719 → 665 tensors
|
| 81 |
+
(exactly 54 stripped).
|
| 82 |
+
|
| 83 |
+
The patch is needed **only at conversion time**. The shipped weights here
|
| 84 |
+
load on plain stock `mlx-lm>=0.31.3` with no patch on your side — that is the
|
| 85 |
+
gap that makes other MLX uploads of this model unusable.
|
| 86 |
+
|
| 87 |
+
> Note: `mlx-lm` 0.29.1 (common on Python 3.9) has **no gemma4 arch at all** —
|
| 88 |
+
> you need 0.31.3+. On Python 3.9 mlx wheels cap at 0.29.3, so use a
|
| 89 |
+
> Python 3.11+/3.13 environment.
|
| 90 |
+
|
| 91 |
+
## Why abliterated
|
| 92 |
+
|
| 93 |
+
Upstream `Jiunsong/supergemma4-e4b-abliterated` removes refusal directions
|
| 94 |
+
from the residual stream of `google/gemma-4-E4B-it`. Upstream release-card
|
| 95 |
+
numbers (vs Google base):
|
| 96 |
+
|
| 97 |
+
| Metric | Google base | SuperGemma4 E4B Abliterated |
|
| 98 |
+
|---|---:|---:|
|
| 99 |
+
| Release quality | 77.46 | 92.34 |
|
| 100 |
+
| Exact overall | 83.50 | 98.50 |
|
| 101 |
+
| JSON exact | 50.0 | 100.0 |
|
| 102 |
+
|
| 103 |
+
Source: [`Jiunsong/supergemma4-e4b-abliterated`](https://huggingface.co/Jiunsong/supergemma4-e4b-abliterated) model card.
|
| 104 |
+
|
| 105 |
+
## What "abliterated" means and doesn't mean
|
| 106 |
+
|
| 107 |
+
- **Does:** reduces reflexive refusals; answers borderline-but-legal requests directly.
|
| 108 |
+
- **Does not:** remove confabulation; alter base knowledge / biases; replace
|
| 109 |
+
your own safety layer at the application boundary.
|
| 110 |
+
|
| 111 |
+
## License — Gemma Terms of Use (must read)
|
| 112 |
+
|
| 113 |
+
Derivative of `google/gemma-4-E4B-it`, governed by the **Gemma Terms of Use**
|
| 114 |
+
(`license: gemma`):
|
| 115 |
+
|
| 116 |
+
- License: https://ai.google.dev/gemma/terms
|
| 117 |
+
- Prohibited use policy: https://ai.google.dev/gemma/prohibited_use_policy
|
| 118 |
+
|
| 119 |
+
By downloading or using these MLX builds you agree to the Gemma Terms of Use
|
| 120 |
+
and Prohibited Use Policy. Redistribution must include the same license terms.
|
| 121 |
+
|
| 122 |
+
## Lineage
|
| 123 |
+
|
| 124 |
+
```
|
| 125 |
+
google/gemma-4-E4B-it
|
| 126 |
+
└── Jiunsong/supergemma4-e4b-abliterated (abliteration + tuning)
|
| 127 |
+
└── dancinlab/supergemma4-e4b-abliterated-MLX-{bf16,4bit,8bit}
|
| 128 |
+
```
|
| 129 |
+
|
| 130 |
+
Conversion: stock `mlx-lm==0.31.3` on Apple Silicon + a convert-time
|
| 131 |
+
`gemma4_text.sanitize` monkey-patch (verbatim `ml-explore/mlx-lm#1240`).
|
| 132 |
+
No mlx-lm / mlx-vlm / transformers fork.
|
| 133 |
+
|
| 134 |
+
## Credits
|
| 135 |
+
|
| 136 |
+
- Upstream model: [`Jiunsong`](https://huggingface.co/Jiunsong)
|
| 137 |
+
- Original base: [`google/gemma-4-E4B-it`](https://huggingface.co/google/gemma-4-E4B-it)
|
| 138 |
+
- MLX conversion + packaging: [`dancinlab`](https://huggingface.co/dancinlab)
|
| 139 |
+
|
| 140 |
+
Everywhere else (llama.cpp / Ollama / LM Studio): [`dancinlab/supergemma4-e4b-abliterated-GGUF`](https://huggingface.co/dancinlab/supergemma4-e4b-abliterated-GGUF) — Q2_K → BF16 + imatrix IQ.
|
| 141 |
+
|
| 142 |
+
Collection: [`dancinlab/uncensored`](https://huggingface.co/collections/dancinlab/uncensored-6a080743e6774450ba77a427).
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,352 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- macro format_parameters(properties, required) -%}
|
| 2 |
+
{%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
|
| 3 |
+
{%- set ns = namespace(found_first=false) -%}
|
| 4 |
+
{%- for key, value in properties | dictsort -%}
|
| 5 |
+
{%- set add_comma = false -%}
|
| 6 |
+
{%- if key not in standard_keys -%}
|
| 7 |
+
{%- if ns.found_first %},{% endif -%}
|
| 8 |
+
{%- set ns.found_first = true -%}
|
| 9 |
+
{{ key }}:{
|
| 10 |
+
{%- if value['description'] -%}
|
| 11 |
+
description:<|"|>{{ value['description'] }}<|"|>
|
| 12 |
+
{%- set add_comma = true -%}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- if value['type'] | upper == 'STRING' -%}
|
| 15 |
+
{%- if value['enum'] -%}
|
| 16 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 17 |
+
enum:{{ format_argument(value['enum']) }}
|
| 18 |
+
{%- endif -%}
|
| 19 |
+
{%- elif value['type'] | upper == 'ARRAY' -%}
|
| 20 |
+
{%- if value['items'] is mapping and value['items'] -%}
|
| 21 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 22 |
+
items:{
|
| 23 |
+
{%- set ns_items = namespace(found_first=false) -%}
|
| 24 |
+
{%- for item_key, item_value in value['items'] | dictsort -%}
|
| 25 |
+
{%- if item_value is not none -%}
|
| 26 |
+
{%- if ns_items.found_first %},{% endif -%}
|
| 27 |
+
{%- set ns_items.found_first = true -%}
|
| 28 |
+
{%- if item_key == 'properties' -%}
|
| 29 |
+
properties:{
|
| 30 |
+
{%- if item_value is mapping -%}
|
| 31 |
+
{{- format_parameters(item_value, value['items']['required'] | default([])) -}}
|
| 32 |
+
{%- endif -%}
|
| 33 |
+
}
|
| 34 |
+
{%- elif item_key == 'required' -%}
|
| 35 |
+
required:[
|
| 36 |
+
{%- for req_item in item_value -%}
|
| 37 |
+
<|"|>{{- req_item -}}<|"|>
|
| 38 |
+
{%- if not loop.last %},{% endif -%}
|
| 39 |
+
{%- endfor -%}
|
| 40 |
+
]
|
| 41 |
+
{%- elif item_key == 'type' -%}
|
| 42 |
+
{%- if item_value is string -%}
|
| 43 |
+
type:{{ format_argument(item_value | upper) }}
|
| 44 |
+
{%- else -%}
|
| 45 |
+
type:{{ format_argument(item_value | map('upper') | list) }}
|
| 46 |
+
{%- endif -%}
|
| 47 |
+
{%- else -%}
|
| 48 |
+
{{ item_key }}:{{ format_argument(item_value) }}
|
| 49 |
+
{%- endif -%}
|
| 50 |
+
{%- endif -%}
|
| 51 |
+
{%- endfor -%}
|
| 52 |
+
}
|
| 53 |
+
{%- endif -%}
|
| 54 |
+
{%- endif -%}
|
| 55 |
+
{%- if value['nullable'] %}
|
| 56 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 57 |
+
nullable:true
|
| 58 |
+
{%- endif -%}
|
| 59 |
+
{%- if value['type'] | upper == 'OBJECT' -%}
|
| 60 |
+
{%- if value['properties'] is defined and value['properties'] is mapping -%}
|
| 61 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 62 |
+
properties:{
|
| 63 |
+
{{- format_parameters(value['properties'], value['required'] | default([])) -}}
|
| 64 |
+
}
|
| 65 |
+
{%- elif value is mapping -%}
|
| 66 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 67 |
+
properties:{
|
| 68 |
+
{{- format_parameters(value, value['required'] | default([])) -}}
|
| 69 |
+
}
|
| 70 |
+
{%- endif -%}
|
| 71 |
+
{%- if value['required'] -%}
|
| 72 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 73 |
+
required:[
|
| 74 |
+
{%- for item in value['required'] | default([]) -%}
|
| 75 |
+
<|"|>{{- item -}}<|"|>
|
| 76 |
+
{%- if not loop.last %},{% endif -%}
|
| 77 |
+
{%- endfor -%}
|
| 78 |
+
]
|
| 79 |
+
{%- endif -%}
|
| 80 |
+
{%- endif -%}
|
| 81 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 82 |
+
type:<|"|>{{ value['type'] | upper }}<|"|>}
|
| 83 |
+
{%- endif -%}
|
| 84 |
+
{%- endfor -%}
|
| 85 |
+
{%- endmacro -%}
|
| 86 |
+
{%- macro format_function_declaration(tool_data) -%}
|
| 87 |
+
declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
|
| 88 |
+
{%- set params = tool_data['function']['parameters'] -%}
|
| 89 |
+
{%- if params -%}
|
| 90 |
+
,parameters:{
|
| 91 |
+
{%- if params['properties'] -%}
|
| 92 |
+
properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
|
| 93 |
+
{%- endif -%}
|
| 94 |
+
{%- if params['required'] -%}
|
| 95 |
+
required:[
|
| 96 |
+
{%- for item in params['required'] -%}
|
| 97 |
+
<|"|>{{- item -}}<|"|>
|
| 98 |
+
{{- ',' if not loop.last -}}
|
| 99 |
+
{%- endfor -%}
|
| 100 |
+
],
|
| 101 |
+
{%- endif -%}
|
| 102 |
+
{%- if params['type'] -%}
|
| 103 |
+
type:<|"|>{{- params['type'] | upper -}}<|"|>}
|
| 104 |
+
{%- endif -%}
|
| 105 |
+
{%- endif -%}
|
| 106 |
+
{%- if 'response' in tool_data['function'] -%}
|
| 107 |
+
{%- set response_declaration = tool_data['function']['response'] -%}
|
| 108 |
+
,response:{
|
| 109 |
+
{%- if response_declaration['description'] -%}
|
| 110 |
+
description:<|"|>{{- response_declaration['description'] -}}<|"|>,
|
| 111 |
+
{%- endif -%}
|
| 112 |
+
{%- if response_declaration['type'] | upper == 'OBJECT' -%}
|
| 113 |
+
type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
|
| 114 |
+
{%- endif -%}
|
| 115 |
+
{%- endif -%}
|
| 116 |
+
}
|
| 117 |
+
{%- endmacro -%}
|
| 118 |
+
{%- macro format_argument(argument, escape_keys=True) -%}
|
| 119 |
+
{%- if argument is string -%}
|
| 120 |
+
{{- '<|"|>' + argument + '<|"|>' -}}
|
| 121 |
+
{%- elif argument is boolean -%}
|
| 122 |
+
{{- 'true' if argument else 'false' -}}
|
| 123 |
+
{%- elif argument is mapping -%}
|
| 124 |
+
{{- '{' -}}
|
| 125 |
+
{%- set ns = namespace(found_first=false) -%}
|
| 126 |
+
{%- for key, value in argument | dictsort -%}
|
| 127 |
+
{%- if ns.found_first %},{% endif -%}
|
| 128 |
+
{%- set ns.found_first = true -%}
|
| 129 |
+
{%- if escape_keys -%}
|
| 130 |
+
{{- '<|"|>' + key + '<|"|>' -}}
|
| 131 |
+
{%- else -%}
|
| 132 |
+
{{- key -}}
|
| 133 |
+
{%- endif -%}
|
| 134 |
+
:{{- format_argument(value, escape_keys=escape_keys) -}}
|
| 135 |
+
{%- endfor -%}
|
| 136 |
+
{{- '}' -}}
|
| 137 |
+
{%- elif argument is sequence -%}
|
| 138 |
+
{{- '[' -}}
|
| 139 |
+
{%- for item in argument -%}
|
| 140 |
+
{{- format_argument(item, escape_keys=escape_keys) -}}
|
| 141 |
+
{%- if not loop.last %},{% endif -%}
|
| 142 |
+
{%- endfor -%}
|
| 143 |
+
{{- ']' -}}
|
| 144 |
+
{%- else -%}
|
| 145 |
+
{{- argument -}}
|
| 146 |
+
{%- endif -%}
|
| 147 |
+
{%- endmacro -%}
|
| 148 |
+
{%- macro strip_thinking(text) -%}
|
| 149 |
+
{%- set ns = namespace(result='') -%}
|
| 150 |
+
{%- for part in text.split('<channel|>') -%}
|
| 151 |
+
{%- if '<|channel>' in part -%}
|
| 152 |
+
{%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
|
| 153 |
+
{%- else -%}
|
| 154 |
+
{%- set ns.result = ns.result + part -%}
|
| 155 |
+
{%- endif -%}
|
| 156 |
+
{%- endfor -%}
|
| 157 |
+
{{- ns.result | trim -}}
|
| 158 |
+
{%- endmacro -%}
|
| 159 |
+
|
| 160 |
+
{%- macro format_tool_response_block(tool_name, response) -%}
|
| 161 |
+
{{- '<|tool_response>' -}}
|
| 162 |
+
{%- if response is mapping -%}
|
| 163 |
+
{{- 'response:' + tool_name + '{' -}}
|
| 164 |
+
{%- for key, value in response | dictsort -%}
|
| 165 |
+
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
| 166 |
+
{%- if not loop.last %},{% endif -%}
|
| 167 |
+
{%- endfor -%}
|
| 168 |
+
{{- '}' -}}
|
| 169 |
+
{%- else -%}
|
| 170 |
+
{{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
|
| 171 |
+
{%- endif -%}
|
| 172 |
+
{{- '<tool_response|>' -}}
|
| 173 |
+
{%- endmacro -%}
|
| 174 |
+
|
| 175 |
+
{%- set ns = namespace(prev_message_type=None) -%}
|
| 176 |
+
{%- set loop_messages = messages -%}
|
| 177 |
+
{%- set default_response_contract -%}
|
| 178 |
+
You are a precise coding assistant.
|
| 179 |
+
- When the user asks for raw JSON or a JSON tool call, return raw JSON only with no markdown fences or commentary.
|
| 180 |
+
- When the user asks for code only, return concise runnable code only with no explanation or docstring unless explicitly requested.
|
| 181 |
+
- Prefer the shortest valid answer that satisfies the requested schema or signature.
|
| 182 |
+
{%- endset -%}
|
| 183 |
+
{{- bos_token -}}
|
| 184 |
+
{#- Handle System/Tool Definitions Block -#}
|
| 185 |
+
{%- if true -%}
|
| 186 |
+
{{- '<|turn>system\n' -}}
|
| 187 |
+
|
| 188 |
+
{#- Inject Thinking token at the very top of the FIRST system turn -#}
|
| 189 |
+
{%- if enable_thinking is defined and enable_thinking -%}
|
| 190 |
+
{{- '<|think|>\n' -}}
|
| 191 |
+
{%- set ns.prev_message_type = 'think' -%}
|
| 192 |
+
{%- endif -%}
|
| 193 |
+
|
| 194 |
+
{{- default_response_contract | trim -}}
|
| 195 |
+
{%- if messages[0]['role'] in ['system', 'developer'] -%}
|
| 196 |
+
{{- '\n\n' -}}
|
| 197 |
+
{{- messages[0]['content'] | trim -}}
|
| 198 |
+
{%- set loop_messages = messages[1:] -%}
|
| 199 |
+
{%- endif -%}
|
| 200 |
+
|
| 201 |
+
{%- if tools -%}
|
| 202 |
+
{%- for tool in tools %}
|
| 203 |
+
{{- '<|tool>' -}}
|
| 204 |
+
{{- format_function_declaration(tool) | trim -}}
|
| 205 |
+
{{- '<tool|>' -}}
|
| 206 |
+
{%- endfor %}
|
| 207 |
+
{%- set ns.prev_message_type = 'tool' -%}
|
| 208 |
+
{%- endif -%}
|
| 209 |
+
|
| 210 |
+
{{- '<turn|>\n' -}}
|
| 211 |
+
{%- endif %}
|
| 212 |
+
|
| 213 |
+
{#- Pre-scan: find last user message index for reasoning guard -#}
|
| 214 |
+
{%- set ns_turn = namespace(last_user_idx=-1) -%}
|
| 215 |
+
{%- for i in range(loop_messages | length) -%}
|
| 216 |
+
{%- if loop_messages[i]['role'] == 'user' -%}
|
| 217 |
+
{%- set ns_turn.last_user_idx = i -%}
|
| 218 |
+
{%- endif -%}
|
| 219 |
+
{%- endfor -%}
|
| 220 |
+
|
| 221 |
+
{#- Loop through messages -#}
|
| 222 |
+
{%- for message in loop_messages -%}
|
| 223 |
+
{%- if message['role'] != 'tool' -%}
|
| 224 |
+
{%- set ns.prev_message_type = None -%}
|
| 225 |
+
{%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
|
| 226 |
+
{#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
|
| 227 |
+
{%- set prev_nt = namespace(role=None, found=false) -%}
|
| 228 |
+
{%- if loop.index0 > 0 -%}
|
| 229 |
+
{%- for j in range(loop.index0 - 1, -1, -1) -%}
|
| 230 |
+
{%- if not prev_nt.found -%}
|
| 231 |
+
{%- if loop_messages[j]['role'] != 'tool' -%}
|
| 232 |
+
{%- set prev_nt.role = loop_messages[j]['role'] -%}
|
| 233 |
+
{%- set prev_nt.found = true -%}
|
| 234 |
+
{%- endif -%}
|
| 235 |
+
{%- endif -%}
|
| 236 |
+
{%- endfor -%}
|
| 237 |
+
{%- endif -%}
|
| 238 |
+
{%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
|
| 239 |
+
{%- if not continue_same_model_turn -%}
|
| 240 |
+
{{- '<|turn>' + role + '\n' }}
|
| 241 |
+
{%- endif -%}
|
| 242 |
+
|
| 243 |
+
{#- Render reasoning/reasoning_content as thinking channel -#}
|
| 244 |
+
{%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
|
| 245 |
+
{%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
|
| 246 |
+
{{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
|
| 247 |
+
{%- endif -%}
|
| 248 |
+
|
| 249 |
+
{%- if message['tool_calls'] -%}
|
| 250 |
+
{%- for tool_call in message['tool_calls'] -%}
|
| 251 |
+
{%- set function = tool_call['function'] -%}
|
| 252 |
+
{{- '<|tool_call>call:' + function['name'] + '{' -}}
|
| 253 |
+
{%- if function['arguments'] is mapping -%}
|
| 254 |
+
{%- set ns_args = namespace(found_first=false) -%}
|
| 255 |
+
{%- for key, value in function['arguments'] | dictsort -%}
|
| 256 |
+
{%- if ns_args.found_first %},{% endif -%}
|
| 257 |
+
{%- set ns_args.found_first = true -%}
|
| 258 |
+
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
| 259 |
+
{%- endfor -%}
|
| 260 |
+
{%- elif function['arguments'] is string -%}
|
| 261 |
+
{{- function['arguments'] -}}
|
| 262 |
+
{%- endif -%}
|
| 263 |
+
{{- '}<tool_call|>' -}}
|
| 264 |
+
{%- endfor -%}
|
| 265 |
+
{%- set ns.prev_message_type = 'tool_call' -%}
|
| 266 |
+
{%- endif -%}
|
| 267 |
+
|
| 268 |
+
{%- set ns_tr_out = namespace(flag=false) -%}
|
| 269 |
+
{%- if message.get('tool_responses') -%}
|
| 270 |
+
{#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
|
| 271 |
+
{%- for tool_response in message['tool_responses'] -%}
|
| 272 |
+
{{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
|
| 273 |
+
{%- set ns_tr_out.flag = true -%}
|
| 274 |
+
{%- set ns.prev_message_type = 'tool_response' -%}
|
| 275 |
+
{%- endfor -%}
|
| 276 |
+
{%- elif message.get('tool_calls') -%}
|
| 277 |
+
{#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
|
| 278 |
+
{%- set ns_tool_scan = namespace(stopped=false) -%}
|
| 279 |
+
{%- for k in range(loop.index0 + 1, loop_messages | length) -%}
|
| 280 |
+
{%- if ns_tool_scan.stopped -%}
|
| 281 |
+
{%- elif loop_messages[k]['role'] != 'tool' -%}
|
| 282 |
+
{%- set ns_tool_scan.stopped = true -%}
|
| 283 |
+
{%- else -%}
|
| 284 |
+
{%- set follow = loop_messages[k] -%}
|
| 285 |
+
{#- Resolve tool_call_id to function name -#}
|
| 286 |
+
{%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
|
| 287 |
+
{%- for tc in message['tool_calls'] -%}
|
| 288 |
+
{%- if tc.get('id') == follow.get('tool_call_id') -%}
|
| 289 |
+
{%- set ns_tname.name = tc['function']['name'] -%}
|
| 290 |
+
{%- endif -%}
|
| 291 |
+
{%- endfor -%}
|
| 292 |
+
{#- Handle content as string or content-parts array -#}
|
| 293 |
+
{%- set tool_body = follow.get('content') -%}
|
| 294 |
+
{%- if tool_body is string -%}
|
| 295 |
+
{{- format_tool_response_block(ns_tname.name, tool_body) -}}
|
| 296 |
+
{%- elif tool_body is sequence and tool_body is not string -%}
|
| 297 |
+
{%- set ns_txt = namespace(s='') -%}
|
| 298 |
+
{%- for part in tool_body -%}
|
| 299 |
+
{%- if part.get('type') == 'text' -%}
|
| 300 |
+
{%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
|
| 301 |
+
{%- endif -%}
|
| 302 |
+
{%- endfor -%}
|
| 303 |
+
{{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
|
| 304 |
+
{%- else -%}
|
| 305 |
+
{{- format_tool_response_block(ns_tname.name, tool_body) -}}
|
| 306 |
+
{%- endif -%}
|
| 307 |
+
{%- set ns_tr_out.flag = true -%}
|
| 308 |
+
{%- set ns.prev_message_type = 'tool_response' -%}
|
| 309 |
+
{%- endif -%}
|
| 310 |
+
{%- endfor -%}
|
| 311 |
+
{%- endif -%}
|
| 312 |
+
|
| 313 |
+
{%- if message['content'] is string -%}
|
| 314 |
+
{%- if role == 'model' -%}
|
| 315 |
+
{{- strip_thinking(message['content']) -}}
|
| 316 |
+
{%- else -%}
|
| 317 |
+
{{- message['content'] | trim -}}
|
| 318 |
+
{%- endif -%}
|
| 319 |
+
{%- elif message['content'] is sequence -%}
|
| 320 |
+
{%- for item in message['content'] -%}
|
| 321 |
+
{%- if item['type'] == 'text' -%}
|
| 322 |
+
{%- if role == 'model' -%}
|
| 323 |
+
{{- strip_thinking(item['text']) -}}
|
| 324 |
+
{%- else -%}
|
| 325 |
+
{{- item['text'] | trim -}}
|
| 326 |
+
{%- endif -%}
|
| 327 |
+
{%- elif item['type'] == 'image' -%}
|
| 328 |
+
{{- '<|image|>' -}}
|
| 329 |
+
{%- set ns.prev_message_type = 'image' -%}
|
| 330 |
+
{%- elif item['type'] == 'audio' -%}
|
| 331 |
+
{{- '<|audio|>' -}}
|
| 332 |
+
{%- set ns.prev_message_type = 'audio' -%}
|
| 333 |
+
{%- elif item['type'] == 'video' -%}
|
| 334 |
+
{{- '<|video|>' -}}
|
| 335 |
+
{%- set ns.prev_message_type = 'video' -%}
|
| 336 |
+
{%- endif -%}
|
| 337 |
+
{%- endfor -%}
|
| 338 |
+
{%- endif -%}
|
| 339 |
+
|
| 340 |
+
{%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
|
| 341 |
+
{{- '<|tool_response>' -}}
|
| 342 |
+
{%- elif not (ns_tr_out.flag and not message.get('content')) -%}
|
| 343 |
+
{{- '<turn|>\n' -}}
|
| 344 |
+
{%- endif -%}
|
| 345 |
+
{%- endif -%}
|
| 346 |
+
{%- endfor -%}
|
| 347 |
+
|
| 348 |
+
{%- if add_generation_prompt -%}
|
| 349 |
+
{%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
|
| 350 |
+
{{- '<|turn>model\n' -}}
|
| 351 |
+
{%- endif -%}
|
| 352 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma4ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": {
|
| 6 |
+
"_name_or_path": "",
|
| 7 |
+
"architectures": null,
|
| 8 |
+
"attention_chunk_size": 12,
|
| 9 |
+
"attention_context_left": 13,
|
| 10 |
+
"attention_context_right": 0,
|
| 11 |
+
"attention_invalid_logits_value": -1000000000.0,
|
| 12 |
+
"attention_logit_cap": 50.0,
|
| 13 |
+
"chunk_size_feed_forward": 0,
|
| 14 |
+
"conv_kernel_size": 5,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"gradient_clipping": 10000000000.0,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 1024,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "LABEL_0",
|
| 21 |
+
"1": "LABEL_1"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"is_encoder_decoder": false,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1
|
| 28 |
+
},
|
| 29 |
+
"model_type": "gemma4_audio",
|
| 30 |
+
"num_attention_heads": 8,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"output_attentions": false,
|
| 33 |
+
"output_hidden_states": false,
|
| 34 |
+
"output_proj_dims": 1536,
|
| 35 |
+
"problem_type": null,
|
| 36 |
+
"residual_weight": 0.5,
|
| 37 |
+
"return_dict": true,
|
| 38 |
+
"rms_norm_eps": 1e-06,
|
| 39 |
+
"subsampling_conv_channels": [
|
| 40 |
+
128,
|
| 41 |
+
32
|
| 42 |
+
],
|
| 43 |
+
"use_clipped_linears": true
|
| 44 |
+
},
|
| 45 |
+
"audio_token_id": 258881,
|
| 46 |
+
"boa_token_id": 256000,
|
| 47 |
+
"boi_token_id": 255999,
|
| 48 |
+
"dtype": "bfloat16",
|
| 49 |
+
"eoa_token_id": 258883,
|
| 50 |
+
"eoa_token_index": 258883,
|
| 51 |
+
"eoi_token_id": 258882,
|
| 52 |
+
"eos_token_id": [
|
| 53 |
+
1,
|
| 54 |
+
106,
|
| 55 |
+
50
|
| 56 |
+
],
|
| 57 |
+
"image_token_id": 258880,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"model_type": "gemma4",
|
| 60 |
+
"text_config": {
|
| 61 |
+
"attention_bias": false,
|
| 62 |
+
"attention_dropout": 0.0,
|
| 63 |
+
"attention_k_eq_v": false,
|
| 64 |
+
"bos_token_id": 2,
|
| 65 |
+
"dtype": "bfloat16",
|
| 66 |
+
"enable_moe_block": false,
|
| 67 |
+
"eos_token_id": 1,
|
| 68 |
+
"expert_intermediate_size": null,
|
| 69 |
+
"final_logit_softcapping": 30.0,
|
| 70 |
+
"global_head_dim": 512,
|
| 71 |
+
"head_dim": 256,
|
| 72 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 73 |
+
"hidden_size": 2560,
|
| 74 |
+
"hidden_size_per_layer_input": 256,
|
| 75 |
+
"initializer_range": 0.02,
|
| 76 |
+
"intermediate_size": 10240,
|
| 77 |
+
"layer_types": [
|
| 78 |
+
"sliding_attention",
|
| 79 |
+
"sliding_attention",
|
| 80 |
+
"sliding_attention",
|
| 81 |
+
"sliding_attention",
|
| 82 |
+
"sliding_attention",
|
| 83 |
+
"full_attention",
|
| 84 |
+
"sliding_attention",
|
| 85 |
+
"sliding_attention",
|
| 86 |
+
"sliding_attention",
|
| 87 |
+
"sliding_attention",
|
| 88 |
+
"sliding_attention",
|
| 89 |
+
"full_attention",
|
| 90 |
+
"sliding_attention",
|
| 91 |
+
"sliding_attention",
|
| 92 |
+
"sliding_attention",
|
| 93 |
+
"sliding_attention",
|
| 94 |
+
"sliding_attention",
|
| 95 |
+
"full_attention",
|
| 96 |
+
"sliding_attention",
|
| 97 |
+
"sliding_attention",
|
| 98 |
+
"sliding_attention",
|
| 99 |
+
"sliding_attention",
|
| 100 |
+
"sliding_attention",
|
| 101 |
+
"full_attention",
|
| 102 |
+
"sliding_attention",
|
| 103 |
+
"sliding_attention",
|
| 104 |
+
"sliding_attention",
|
| 105 |
+
"sliding_attention",
|
| 106 |
+
"sliding_attention",
|
| 107 |
+
"full_attention",
|
| 108 |
+
"sliding_attention",
|
| 109 |
+
"sliding_attention",
|
| 110 |
+
"sliding_attention",
|
| 111 |
+
"sliding_attention",
|
| 112 |
+
"sliding_attention",
|
| 113 |
+
"full_attention",
|
| 114 |
+
"sliding_attention",
|
| 115 |
+
"sliding_attention",
|
| 116 |
+
"sliding_attention",
|
| 117 |
+
"sliding_attention",
|
| 118 |
+
"sliding_attention",
|
| 119 |
+
"full_attention"
|
| 120 |
+
],
|
| 121 |
+
"max_position_embeddings": 131072,
|
| 122 |
+
"model_type": "gemma4_text",
|
| 123 |
+
"num_attention_heads": 8,
|
| 124 |
+
"num_experts": null,
|
| 125 |
+
"num_global_key_value_heads": null,
|
| 126 |
+
"num_hidden_layers": 42,
|
| 127 |
+
"num_key_value_heads": 2,
|
| 128 |
+
"num_kv_shared_layers": 18,
|
| 129 |
+
"pad_token_id": 0,
|
| 130 |
+
"rms_norm_eps": 1e-06,
|
| 131 |
+
"rope_parameters": {
|
| 132 |
+
"full_attention": {
|
| 133 |
+
"partial_rotary_factor": 0.25,
|
| 134 |
+
"rope_theta": 1000000.0,
|
| 135 |
+
"rope_type": "proportional"
|
| 136 |
+
},
|
| 137 |
+
"sliding_attention": {
|
| 138 |
+
"rope_theta": 10000.0,
|
| 139 |
+
"rope_type": "default"
|
| 140 |
+
}
|
| 141 |
+
},
|
| 142 |
+
"sliding_window": 512,
|
| 143 |
+
"tie_word_embeddings": true,
|
| 144 |
+
"top_k_experts": null,
|
| 145 |
+
"use_bidirectional_attention": null,
|
| 146 |
+
"use_cache": true,
|
| 147 |
+
"use_double_wide_mlp": false,
|
| 148 |
+
"vocab_size": 262144,
|
| 149 |
+
"vocab_size_per_layer_input": 262144
|
| 150 |
+
},
|
| 151 |
+
"tie_word_embeddings": true,
|
| 152 |
+
"transformers_version": "5.5.0.dev0",
|
| 153 |
+
"video_token_id": 258884,
|
| 154 |
+
"vision_soft_tokens_per_image": 280
|
| 155 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
106,
|
| 7 |
+
50
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"temperature": 1.0,
|
| 11 |
+
"top_k": 64,
|
| 12 |
+
"top_p": 0.95,
|
| 13 |
+
"transformers_version": "5.5.0.dev0"
|
| 14 |
+
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a86d155e54e3279520814c5ac36162fd6b9422b25d6c6767919f779eefc49b6b
|
| 3 |
+
size 5356212683
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2873d06a66aa03baed04d943911da45512fb65e948cc654ec8e6b9eeade9b4ba
|
| 3 |
+
size 3877705438
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6dbb90fb3cc91ade2eeed944dbadec2e1df530ba42276c91a7f239b1a0b9bd1
|
| 3 |
+
size 5637144740
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:410fcc38c87d57848581f972d046b8fe6c47d37edaad4eef60fada1e11188056
|
| 3 |
+
size 55051028
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,673 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14926026836,
|
| 4 |
+
"total_parameters": 7463013376
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"language_model.model.embed_tokens_per_layer.weight": "model-00003-of-00004.safetensors",
|
| 9 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"language_model.model.layers.0.layer_scalar": "model-00001-of-00004.safetensors",
|
| 11 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"language_model.model.layers.0.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"language_model.model.layers.0.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"language_model.model.layers.0.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"language_model.model.layers.1.layer_scalar": "model-00001-of-00004.safetensors",
|
| 28 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"language_model.model.layers.1.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"language_model.model.layers.1.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 34 |
+
"language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 35 |
+
"language_model.model.layers.1.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 37 |
+
"language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 38 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 39 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 40 |
+
"language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 41 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 42 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 43 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 44 |
+
"language_model.model.layers.10.layer_scalar": "model-00001-of-00004.safetensors",
|
| 45 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 46 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 47 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 48 |
+
"language_model.model.layers.10.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 49 |
+
"language_model.model.layers.10.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 50 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 51 |
+
"language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 52 |
+
"language_model.model.layers.10.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 53 |
+
"language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 54 |
+
"language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 55 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 56 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 57 |
+
"language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 58 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 59 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 60 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 61 |
+
"language_model.model.layers.11.layer_scalar": "model-00001-of-00004.safetensors",
|
| 62 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 63 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 64 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 65 |
+
"language_model.model.layers.11.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 66 |
+
"language_model.model.layers.11.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 67 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 68 |
+
"language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 69 |
+
"language_model.model.layers.11.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 70 |
+
"language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 71 |
+
"language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 72 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 73 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 74 |
+
"language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 75 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 76 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 77 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 78 |
+
"language_model.model.layers.12.layer_scalar": "model-00001-of-00004.safetensors",
|
| 79 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 80 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 81 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 82 |
+
"language_model.model.layers.12.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 83 |
+
"language_model.model.layers.12.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 84 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 85 |
+
"language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 86 |
+
"language_model.model.layers.12.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 87 |
+
"language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 88 |
+
"language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 89 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 90 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 91 |
+
"language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 92 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 93 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 94 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 95 |
+
"language_model.model.layers.13.layer_scalar": "model-00001-of-00004.safetensors",
|
| 96 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 97 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 98 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 99 |
+
"language_model.model.layers.13.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 100 |
+
"language_model.model.layers.13.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 101 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 102 |
+
"language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 103 |
+
"language_model.model.layers.13.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 104 |
+
"language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 105 |
+
"language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 106 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 107 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 108 |
+
"language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 109 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 110 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 111 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 112 |
+
"language_model.model.layers.14.layer_scalar": "model-00001-of-00004.safetensors",
|
| 113 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 114 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 115 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 116 |
+
"language_model.model.layers.14.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 117 |
+
"language_model.model.layers.14.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 118 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 119 |
+
"language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"language_model.model.layers.14.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 121 |
+
"language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 123 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 125 |
+
"language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 126 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 127 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 128 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 129 |
+
"language_model.model.layers.15.layer_scalar": "model-00001-of-00004.safetensors",
|
| 130 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 131 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 132 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 133 |
+
"language_model.model.layers.15.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 134 |
+
"language_model.model.layers.15.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 135 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 136 |
+
"language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 137 |
+
"language_model.model.layers.15.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 138 |
+
"language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 139 |
+
"language_model.model.layers.15.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 140 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 141 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"language_model.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"language_model.model.layers.16.layer_scalar": "model-00001-of-00004.safetensors",
|
| 147 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"language_model.model.layers.16.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"language_model.model.layers.16.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 153 |
+
"language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"language_model.model.layers.16.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"language_model.model.layers.16.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 159 |
+
"language_model.model.layers.16.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 162 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 163 |
+
"language_model.model.layers.17.layer_scalar": "model-00001-of-00004.safetensors",
|
| 164 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 165 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 166 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 167 |
+
"language_model.model.layers.17.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 168 |
+
"language_model.model.layers.17.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 169 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 170 |
+
"language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 171 |
+
"language_model.model.layers.17.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 172 |
+
"language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 173 |
+
"language_model.model.layers.17.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 174 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 175 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 176 |
+
"language_model.model.layers.17.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 177 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 178 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 179 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 180 |
+
"language_model.model.layers.18.layer_scalar": "model-00001-of-00004.safetensors",
|
| 181 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 182 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 183 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 184 |
+
"language_model.model.layers.18.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 185 |
+
"language_model.model.layers.18.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 186 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 187 |
+
"language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 188 |
+
"language_model.model.layers.18.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 189 |
+
"language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 190 |
+
"language_model.model.layers.18.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 191 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 192 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 193 |
+
"language_model.model.layers.18.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 194 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 195 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 196 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 197 |
+
"language_model.model.layers.19.layer_scalar": "model-00001-of-00004.safetensors",
|
| 198 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 199 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 200 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 201 |
+
"language_model.model.layers.19.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 202 |
+
"language_model.model.layers.19.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 203 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 204 |
+
"language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 205 |
+
"language_model.model.layers.19.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 206 |
+
"language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 207 |
+
"language_model.model.layers.19.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 208 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 209 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 210 |
+
"language_model.model.layers.19.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 211 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 212 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 213 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 214 |
+
"language_model.model.layers.2.layer_scalar": "model-00001-of-00004.safetensors",
|
| 215 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 216 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 217 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 218 |
+
"language_model.model.layers.2.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 219 |
+
"language_model.model.layers.2.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 221 |
+
"language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 222 |
+
"language_model.model.layers.2.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 223 |
+
"language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 225 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 226 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 227 |
+
"language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 228 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 229 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 230 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 231 |
+
"language_model.model.layers.20.layer_scalar": "model-00001-of-00004.safetensors",
|
| 232 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 233 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 234 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 235 |
+
"language_model.model.layers.20.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 236 |
+
"language_model.model.layers.20.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 237 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 238 |
+
"language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 239 |
+
"language_model.model.layers.20.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 240 |
+
"language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 241 |
+
"language_model.model.layers.20.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 242 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 243 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 244 |
+
"language_model.model.layers.20.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 245 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 247 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 248 |
+
"language_model.model.layers.21.layer_scalar": "model-00002-of-00004.safetensors",
|
| 249 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 250 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 251 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 252 |
+
"language_model.model.layers.21.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 253 |
+
"language_model.model.layers.21.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 254 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 255 |
+
"language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 256 |
+
"language_model.model.layers.21.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 257 |
+
"language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 258 |
+
"language_model.model.layers.21.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 259 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 260 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"language_model.model.layers.21.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 265 |
+
"language_model.model.layers.22.layer_scalar": "model-00002-of-00004.safetensors",
|
| 266 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 267 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 268 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 269 |
+
"language_model.model.layers.22.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 270 |
+
"language_model.model.layers.22.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 271 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 272 |
+
"language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 273 |
+
"language_model.model.layers.22.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 274 |
+
"language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 275 |
+
"language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 276 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 277 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 278 |
+
"language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 279 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 280 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 281 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 282 |
+
"language_model.model.layers.23.layer_scalar": "model-00002-of-00004.safetensors",
|
| 283 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 284 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 285 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 286 |
+
"language_model.model.layers.23.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 287 |
+
"language_model.model.layers.23.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 290 |
+
"language_model.model.layers.23.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 291 |
+
"language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 292 |
+
"language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 293 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 294 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 297 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 298 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 299 |
+
"language_model.model.layers.24.layer_scalar": "model-00002-of-00004.safetensors",
|
| 300 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 301 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 302 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 303 |
+
"language_model.model.layers.24.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 304 |
+
"language_model.model.layers.24.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 305 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 306 |
+
"language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 307 |
+
"language_model.model.layers.24.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 308 |
+
"language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 309 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 310 |
+
"language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 311 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 312 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 313 |
+
"language_model.model.layers.25.layer_scalar": "model-00002-of-00004.safetensors",
|
| 314 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 315 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 316 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 317 |
+
"language_model.model.layers.25.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 318 |
+
"language_model.model.layers.25.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 319 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"language_model.model.layers.25.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"language_model.model.layers.26.layer_scalar": "model-00002-of-00004.safetensors",
|
| 328 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 329 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 330 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 331 |
+
"language_model.model.layers.26.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 332 |
+
"language_model.model.layers.26.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 333 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"language_model.model.layers.26.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 338 |
+
"language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 339 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 341 |
+
"language_model.model.layers.27.layer_scalar": "model-00002-of-00004.safetensors",
|
| 342 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 344 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 345 |
+
"language_model.model.layers.27.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 346 |
+
"language_model.model.layers.27.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 347 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 348 |
+
"language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 349 |
+
"language_model.model.layers.27.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 350 |
+
"language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 351 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 352 |
+
"language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 353 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 354 |
+
"language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 355 |
+
"language_model.model.layers.28.layer_scalar": "model-00002-of-00004.safetensors",
|
| 356 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 357 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 358 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 359 |
+
"language_model.model.layers.28.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 360 |
+
"language_model.model.layers.28.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 361 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 362 |
+
"language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"language_model.model.layers.28.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 364 |
+
"language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 365 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 367 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 368 |
+
"language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 369 |
+
"language_model.model.layers.29.layer_scalar": "model-00002-of-00004.safetensors",
|
| 370 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 371 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 372 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"language_model.model.layers.29.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"language_model.model.layers.29.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"language_model.model.layers.29.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"language_model.model.layers.3.layer_scalar": "model-00001-of-00004.safetensors",
|
| 384 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"language_model.model.layers.3.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"language_model.model.layers.3.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"language_model.model.layers.3.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 395 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
+
"language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 398 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 399 |
+
"language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"language_model.model.layers.30.layer_scalar": "model-00002-of-00004.safetensors",
|
| 401 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"language_model.model.layers.30.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"language_model.model.layers.30.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 406 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 407 |
+
"language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 408 |
+
"language_model.model.layers.30.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 409 |
+
"language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 410 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 411 |
+
"language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 412 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 413 |
+
"language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 414 |
+
"language_model.model.layers.31.layer_scalar": "model-00002-of-00004.safetensors",
|
| 415 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 416 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 417 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 418 |
+
"language_model.model.layers.31.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 419 |
+
"language_model.model.layers.31.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 420 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 421 |
+
"language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 422 |
+
"language_model.model.layers.31.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 423 |
+
"language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 424 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 425 |
+
"language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 426 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 427 |
+
"language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 428 |
+
"language_model.model.layers.32.layer_scalar": "model-00002-of-00004.safetensors",
|
| 429 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 430 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 431 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 432 |
+
"language_model.model.layers.32.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 433 |
+
"language_model.model.layers.32.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 434 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 435 |
+
"language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 436 |
+
"language_model.model.layers.32.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 437 |
+
"language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 438 |
+
"language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 439 |
+
"language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 440 |
+
"language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 441 |
+
"language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 442 |
+
"language_model.model.layers.33.layer_scalar": "model-00002-of-00004.safetensors",
|
| 443 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 444 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 445 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 446 |
+
"language_model.model.layers.33.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 447 |
+
"language_model.model.layers.33.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 448 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 449 |
+
"language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 450 |
+
"language_model.model.layers.33.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 451 |
+
"language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 452 |
+
"language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 453 |
+
"language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 454 |
+
"language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 455 |
+
"language_model.model.layers.34.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 456 |
+
"language_model.model.layers.34.layer_scalar": "model-00002-of-00004.safetensors",
|
| 457 |
+
"language_model.model.layers.34.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 458 |
+
"language_model.model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 459 |
+
"language_model.model.layers.34.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 460 |
+
"language_model.model.layers.34.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 461 |
+
"language_model.model.layers.34.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 462 |
+
"language_model.model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 463 |
+
"language_model.model.layers.34.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 464 |
+
"language_model.model.layers.34.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 465 |
+
"language_model.model.layers.34.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 466 |
+
"language_model.model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 467 |
+
"language_model.model.layers.34.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 468 |
+
"language_model.model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 469 |
+
"language_model.model.layers.35.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 470 |
+
"language_model.model.layers.35.layer_scalar": "model-00002-of-00004.safetensors",
|
| 471 |
+
"language_model.model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 472 |
+
"language_model.model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 473 |
+
"language_model.model.layers.35.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 474 |
+
"language_model.model.layers.35.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 475 |
+
"language_model.model.layers.35.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 476 |
+
"language_model.model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 477 |
+
"language_model.model.layers.35.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 478 |
+
"language_model.model.layers.35.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 479 |
+
"language_model.model.layers.35.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 480 |
+
"language_model.model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 481 |
+
"language_model.model.layers.35.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 482 |
+
"language_model.model.layers.35.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 483 |
+
"language_model.model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 484 |
+
"language_model.model.layers.36.layer_scalar": "model-00002-of-00004.safetensors",
|
| 485 |
+
"language_model.model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 486 |
+
"language_model.model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 487 |
+
"language_model.model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 488 |
+
"language_model.model.layers.36.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 489 |
+
"language_model.model.layers.36.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 490 |
+
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 491 |
+
"language_model.model.layers.36.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 492 |
+
"language_model.model.layers.36.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 493 |
+
"language_model.model.layers.36.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 494 |
+
"language_model.model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 495 |
+
"language_model.model.layers.36.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 496 |
+
"language_model.model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 497 |
+
"language_model.model.layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 498 |
+
"language_model.model.layers.37.layer_scalar": "model-00002-of-00004.safetensors",
|
| 499 |
+
"language_model.model.layers.37.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 500 |
+
"language_model.model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 501 |
+
"language_model.model.layers.37.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 502 |
+
"language_model.model.layers.37.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 503 |
+
"language_model.model.layers.37.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 504 |
+
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 505 |
+
"language_model.model.layers.37.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 506 |
+
"language_model.model.layers.37.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 507 |
+
"language_model.model.layers.37.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 508 |
+
"language_model.model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 509 |
+
"language_model.model.layers.37.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 510 |
+
"language_model.model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 511 |
+
"language_model.model.layers.38.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 512 |
+
"language_model.model.layers.38.layer_scalar": "model-00002-of-00004.safetensors",
|
| 513 |
+
"language_model.model.layers.38.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 514 |
+
"language_model.model.layers.38.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 515 |
+
"language_model.model.layers.38.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 516 |
+
"language_model.model.layers.38.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 517 |
+
"language_model.model.layers.38.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 518 |
+
"language_model.model.layers.38.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 519 |
+
"language_model.model.layers.38.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 520 |
+
"language_model.model.layers.38.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 521 |
+
"language_model.model.layers.38.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 522 |
+
"language_model.model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 523 |
+
"language_model.model.layers.38.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 524 |
+
"language_model.model.layers.38.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 525 |
+
"language_model.model.layers.39.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 526 |
+
"language_model.model.layers.39.layer_scalar": "model-00002-of-00004.safetensors",
|
| 527 |
+
"language_model.model.layers.39.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 528 |
+
"language_model.model.layers.39.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 529 |
+
"language_model.model.layers.39.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 530 |
+
"language_model.model.layers.39.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 531 |
+
"language_model.model.layers.39.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 532 |
+
"language_model.model.layers.39.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 533 |
+
"language_model.model.layers.39.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 534 |
+
"language_model.model.layers.39.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 535 |
+
"language_model.model.layers.39.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 536 |
+
"language_model.model.layers.39.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 537 |
+
"language_model.model.layers.39.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 538 |
+
"language_model.model.layers.39.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 539 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 540 |
+
"language_model.model.layers.4.layer_scalar": "model-00001-of-00004.safetensors",
|
| 541 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 542 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 543 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 544 |
+
"language_model.model.layers.4.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 545 |
+
"language_model.model.layers.4.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 546 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 547 |
+
"language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"language_model.model.layers.4.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 549 |
+
"language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 550 |
+
"language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 551 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 552 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 553 |
+
"language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 554 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 555 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 556 |
+
"language_model.model.layers.40.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 557 |
+
"language_model.model.layers.40.layer_scalar": "model-00002-of-00004.safetensors",
|
| 558 |
+
"language_model.model.layers.40.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 559 |
+
"language_model.model.layers.40.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 560 |
+
"language_model.model.layers.40.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 561 |
+
"language_model.model.layers.40.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 562 |
+
"language_model.model.layers.40.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 563 |
+
"language_model.model.layers.40.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 564 |
+
"language_model.model.layers.40.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 565 |
+
"language_model.model.layers.40.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 566 |
+
"language_model.model.layers.40.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 567 |
+
"language_model.model.layers.40.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 568 |
+
"language_model.model.layers.40.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 569 |
+
"language_model.model.layers.40.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 570 |
+
"language_model.model.layers.41.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 571 |
+
"language_model.model.layers.41.layer_scalar": "model-00002-of-00004.safetensors",
|
| 572 |
+
"language_model.model.layers.41.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 573 |
+
"language_model.model.layers.41.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 574 |
+
"language_model.model.layers.41.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 575 |
+
"language_model.model.layers.41.per_layer_input_gate.weight": "model-00002-of-00004.safetensors",
|
| 576 |
+
"language_model.model.layers.41.per_layer_projection.weight": "model-00002-of-00004.safetensors",
|
| 577 |
+
"language_model.model.layers.41.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 578 |
+
"language_model.model.layers.41.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 579 |
+
"language_model.model.layers.41.post_per_layer_input_norm.weight": "model-00002-of-00004.safetensors",
|
| 580 |
+
"language_model.model.layers.41.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 581 |
+
"language_model.model.layers.41.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 582 |
+
"language_model.model.layers.41.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 583 |
+
"language_model.model.layers.41.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 584 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 585 |
+
"language_model.model.layers.5.layer_scalar": "model-00001-of-00004.safetensors",
|
| 586 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 587 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 588 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 589 |
+
"language_model.model.layers.5.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 590 |
+
"language_model.model.layers.5.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 591 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 592 |
+
"language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 593 |
+
"language_model.model.layers.5.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 594 |
+
"language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 595 |
+
"language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 597 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 598 |
+
"language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 599 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 600 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 601 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 602 |
+
"language_model.model.layers.6.layer_scalar": "model-00001-of-00004.safetensors",
|
| 603 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 604 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 605 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 606 |
+
"language_model.model.layers.6.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 607 |
+
"language_model.model.layers.6.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 609 |
+
"language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 610 |
+
"language_model.model.layers.6.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 611 |
+
"language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 612 |
+
"language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 613 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 614 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 615 |
+
"language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 616 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 617 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 618 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 619 |
+
"language_model.model.layers.7.layer_scalar": "model-00001-of-00004.safetensors",
|
| 620 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 621 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 622 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 623 |
+
"language_model.model.layers.7.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 624 |
+
"language_model.model.layers.7.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 625 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 626 |
+
"language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 627 |
+
"language_model.model.layers.7.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 628 |
+
"language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 629 |
+
"language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 630 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 631 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 633 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 634 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 635 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 636 |
+
"language_model.model.layers.8.layer_scalar": "model-00001-of-00004.safetensors",
|
| 637 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 638 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 639 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 640 |
+
"language_model.model.layers.8.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 641 |
+
"language_model.model.layers.8.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 642 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 643 |
+
"language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"language_model.model.layers.8.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 645 |
+
"language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 646 |
+
"language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 647 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 648 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 649 |
+
"language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 650 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 651 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 652 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 653 |
+
"language_model.model.layers.9.layer_scalar": "model-00001-of-00004.safetensors",
|
| 654 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 655 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 657 |
+
"language_model.model.layers.9.per_layer_input_gate.weight": "model-00001-of-00004.safetensors",
|
| 658 |
+
"language_model.model.layers.9.per_layer_projection.weight": "model-00001-of-00004.safetensors",
|
| 659 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 660 |
+
"language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 661 |
+
"language_model.model.layers.9.post_per_layer_input_norm.weight": "model-00001-of-00004.safetensors",
|
| 662 |
+
"language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 663 |
+
"language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 664 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 665 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 666 |
+
"language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 667 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 669 |
+
"language_model.model.norm.weight": "model-00002-of-00004.safetensors",
|
| 670 |
+
"language_model.model.per_layer_model_projection.weight": "model-00004-of-00004.safetensors",
|
| 671 |
+
"language_model.model.per_layer_projection_norm.weight": "model-00004-of-00004.safetensors"
|
| 672 |
+
}
|
| 673 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
|
| 3 |
+
size 32169626
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|audio|>",
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"boa_token": "<|audio>",
|
| 5 |
+
"boi_token": "<|image>",
|
| 6 |
+
"bos_token": "<bos>",
|
| 7 |
+
"eoa_token": "<audio|>",
|
| 8 |
+
"eoc_token": "<channel|>",
|
| 9 |
+
"eoi_token": "<image|>",
|
| 10 |
+
"eos_token": "<eos>",
|
| 11 |
+
"eot_token": "<turn|>",
|
| 12 |
+
"escape_token": "<|\"|>",
|
| 13 |
+
"etc_token": "<tool_call|>",
|
| 14 |
+
"etd_token": "<tool|>",
|
| 15 |
+
"etr_token": "<tool_response|>",
|
| 16 |
+
"extra_special_tokens": [
|
| 17 |
+
"<|video|>"
|
| 18 |
+
],
|
| 19 |
+
"image_token": "<|image|>",
|
| 20 |
+
"is_local": true,
|
| 21 |
+
"local_files_only": false,
|
| 22 |
+
"mask_token": "<mask>",
|
| 23 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 24 |
+
"model_specific_special_tokens": {
|
| 25 |
+
"audio_token": "<|audio|>",
|
| 26 |
+
"boa_token": "<|audio>",
|
| 27 |
+
"boi_token": "<|image>",
|
| 28 |
+
"eoa_token": "<audio|>",
|
| 29 |
+
"eoc_token": "<channel|>",
|
| 30 |
+
"eoi_token": "<image|>",
|
| 31 |
+
"eot_token": "<turn|>",
|
| 32 |
+
"escape_token": "<|\"|>",
|
| 33 |
+
"etc_token": "<tool_call|>",
|
| 34 |
+
"etd_token": "<tool|>",
|
| 35 |
+
"etr_token": "<tool_response|>",
|
| 36 |
+
"image_token": "<|image|>",
|
| 37 |
+
"soc_token": "<|channel>",
|
| 38 |
+
"sot_token": "<|turn>",
|
| 39 |
+
"stc_token": "<|tool_call>",
|
| 40 |
+
"std_token": "<|tool>",
|
| 41 |
+
"str_token": "<|tool_response>",
|
| 42 |
+
"think_token": "<|think|>"
|
| 43 |
+
},
|
| 44 |
+
"pad_token": "<pad>",
|
| 45 |
+
"padding_side": "left",
|
| 46 |
+
"processor_class": "Gemma4Processor",
|
| 47 |
+
"response_schema": {
|
| 48 |
+
"properties": {
|
| 49 |
+
"content": {
|
| 50 |
+
"type": "string"
|
| 51 |
+
},
|
| 52 |
+
"role": {
|
| 53 |
+
"const": "assistant"
|
| 54 |
+
},
|
| 55 |
+
"thinking": {
|
| 56 |
+
"type": "string"
|
| 57 |
+
},
|
| 58 |
+
"tool_calls": {
|
| 59 |
+
"items": {
|
| 60 |
+
"properties": {
|
| 61 |
+
"function": {
|
| 62 |
+
"properties": {
|
| 63 |
+
"arguments": {
|
| 64 |
+
"additionalProperties": {},
|
| 65 |
+
"type": "object",
|
| 66 |
+
"x-parser": "gemma4-tool-call"
|
| 67 |
+
},
|
| 68 |
+
"name": {
|
| 69 |
+
"type": "string"
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
+
"type": "object",
|
| 73 |
+
"x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
|
| 74 |
+
},
|
| 75 |
+
"type": {
|
| 76 |
+
"const": "function"
|
| 77 |
+
}
|
| 78 |
+
},
|
| 79 |
+
"type": "object"
|
| 80 |
+
},
|
| 81 |
+
"type": "array",
|
| 82 |
+
"x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
|
| 83 |
+
}
|
| 84 |
+
},
|
| 85 |
+
"type": "object",
|
| 86 |
+
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
|
| 87 |
+
},
|
| 88 |
+
"soc_token": "<|channel>",
|
| 89 |
+
"sot_token": "<|turn>",
|
| 90 |
+
"stc_token": "<|tool_call>",
|
| 91 |
+
"std_token": "<|tool>",
|
| 92 |
+
"str_token": "<|tool_response>",
|
| 93 |
+
"think_token": "<|think|>",
|
| 94 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 95 |
+
"tool_parser_type": "gemma4",
|
| 96 |
+
"unk_token": "<unk>"
|
| 97 |
+
}
|