Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00003.bs filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00003.bs filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00003.bs filter=lfs diff=lfs merge=lfs -text
+tokenizer.model.v3 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,41 @@
+---
+license: apache-2.0
+tags:
+- bigsmall
+- compression
+- lossless
+- mistral
+---
+# Mistral 7B Instruct v0.3 (BigSmall compressed)
+
+Mistral 7B Instruct v0.3 compressed with [BigSmall](https://github.com/wpferrell/Bigsmall) — lossless neural network weight compression.
+
+**14 GB → 9.3 GB. Bit-for-bit identical weights. No quality loss.**
+
+## Usage
+pip install bigsmall
+
+```python
+import bigsmall
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+state_dict = bigsmall.from_pretrained("wpferrell/mistral-7b-instruct-bigsmall")
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3", state_dict=state_dict)
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
+```
+
+Or stream layer-by-layer with under 2GB peak RAM:
+```python
+with bigsmall.StreamingLoader("model.bs", device="cuda") as loader:
+    for layer_idx, tensors in loader.iter_layers():
+        pass
+```
+
+## Compression stats
+- Original: ~14.2 GB (BF16)
+- Compressed: ~9.3 GB
+- Ratio: ~65.6% (lossless)
+- All tensors md5-verified bit-identical
+
+## About BigSmall
+pip install bigsmall | https://github.com/wpferrell/Bigsmall

bigsmall.index.json

@@ -0,0 +1,312 @@
+{
+  "metadata": {
+    "bigsmall_version": "1.0.0",
+    "container_version": 1,
+    "format": "bf16",
+    "mode": "balanced",
+    "model_type": "llm",
+    "total_size": 9519443437,
+    "total_raw_size": 14496047104,
+    "ratio_pct": 65.66923636977718,
+    "shard_count": 3,
+    "tensor_count": 291,
+    "shards": [
+      "model-00001-of-00003.bs",
+      "model-00002-of-00003.bs",
+      "model-00003-of-00003.bs"
+    ]
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.bs",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.bs",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.bs",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.bs",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.bs",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.bs",
+    "lm_head.weight": "model-00003-of-00003.bs",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.bs",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.bs",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.bs",
+    "model.norm.weight": "model-00003-of-00003.bs"
+  }
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.42.0.dev0"
+}

model-00001-of-00003.bs

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad9ff9c8422423d6413b8fa03f02ed7c85617355065d32982aeb291ba549066
+size 3254524712

model-00002-of-00003.bs

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8dbe42c017220bf5ec124eaa881c5a31ba624361e15978f71ddec7d97f861ff
+size 3283809454

model-00003-of-00003.bs

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e54fbfbc980f9745f81b36e487daa4d8511d28d12ba577f0deb7184342d7d8
+size 2981109271

params.json

@@ -0,0 +1,11 @@
+{
+    "dim": 4096,
+    "n_layers": 32,
+    "head_dim": 128,
+    "hidden_dim": 14336,
+    "n_heads": 32,
+    "n_kv_heads": 8,
+    "norm_eps": 1e-05,
+    "vocab_size": 32768,
+    "rope_theta": 1000000.0
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

tokenizer.model.v3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404