Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +1 -0
- chat_template.jinja +3 -0
- config.json +574 -0
- generation_config.json +9 -0
- model-00001-of-00071.safetensors +3 -0
- model-00002-of-00071.safetensors +3 -0
- model-00003-of-00071.safetensors +3 -0
- model-00004-of-00071.safetensors +3 -0
- model-00005-of-00071.safetensors +3 -0
- model-00006-of-00071.safetensors +3 -0
- model-00007-of-00071.safetensors +3 -0
- model-00008-of-00071.safetensors +3 -0
- model-00009-of-00071.safetensors +3 -0
- model-00010-of-00071.safetensors +3 -0
- model-00011-of-00071.safetensors +3 -0
- model-00012-of-00071.safetensors +3 -0
- model-00013-of-00071.safetensors +3 -0
- model-00014-of-00071.safetensors +3 -0
- model-00015-of-00071.safetensors +3 -0
- model-00016-of-00071.safetensors +3 -0
- model-00017-of-00071.safetensors +3 -0
- model-00018-of-00071.safetensors +3 -0
- model-00019-of-00071.safetensors +3 -0
- model-00020-of-00071.safetensors +3 -0
- model-00021-of-00071.safetensors +3 -0
- model-00022-of-00071.safetensors +3 -0
- model-00023-of-00071.safetensors +3 -0
- model-00024-of-00071.safetensors +3 -0
- model-00025-of-00071.safetensors +3 -0
- model-00026-of-00071.safetensors +3 -0
- model-00027-of-00071.safetensors +3 -0
- model-00028-of-00071.safetensors +3 -0
- model-00029-of-00071.safetensors +3 -0
- model-00030-of-00071.safetensors +3 -0
- model-00031-of-00071.safetensors +3 -0
- model-00032-of-00071.safetensors +3 -0
- model-00033-of-00071.safetensors +3 -0
- model-00034-of-00071.safetensors +3 -0
- model-00035-of-00071.safetensors +3 -0
- model-00036-of-00071.safetensors +3 -0
- model-00037-of-00071.safetensors +3 -0
- model-00038-of-00071.safetensors +3 -0
- model-00039-of-00071.safetensors +3 -0
- model-00040-of-00071.safetensors +3 -0
- model-00041-of-00071.safetensors +3 -0
- model-00042-of-00071.safetensors +3 -0
- model-00043-of-00071.safetensors +3 -0
- model-00044-of-00071.safetensors +3 -0
- model-00045-of-00071.safetensors +3 -0
- model-00046-of-00071.safetensors +3 -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 |
+
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if not thinking is defined %}{% set thinking = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, system_prompt='', is_first_sp=true, is_last_user=false, is_only_sys=false, is_prefix=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '
|
| 2 |
+
|
| 3 |
+
' + message['content'] %}{%- endif %}{% set ns.is_only_sys = true %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- if ns.is_last_user or ns.is_only_sys %}{{'<|Assistant|></think>'}}{%- endif %}{%- set ns.is_last_user = false -%}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<|tool▁calls▁begin|><|tool▁call▁begin|>'+ tool['function']['name'] + '<|tool▁sep|>' + tool['function']['arguments'] + '<|tool▁call▁end|>'}}{%- else %}{{message['content'] + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['function']['name'] + '<|tool▁sep|>' + tool['function']['arguments'] + '<|tool▁call▁end|>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'<|tool▁call▁begin|>'+ tool['function']['name'] + '<|tool▁sep|>' + tool['function']['arguments'] + '<|tool▁call▁end|>'}}{%- endif %}{%- endfor %}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}{%- if ns.is_last_user %}{{'<|Assistant|>'}}{%- if message['prefix'] is defined and message['prefix'] and thinking %}{{'<think>'}}{%- else %}{{'</think>'}}{%- endif %}{%- endif %}{%- if message['prefix'] is defined and message['prefix'] %}{%- set ns.is_prefix = true -%}{%- endif %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{%- set content = message['content'] -%}{%- if '</think>' in content %}{%- set content = content.split('</think>', 1)[1] -%}{%- endif %}{{content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{{'<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- if message['role'] != 'system' %}{% set ns.is_only_sys = false %}{%- endif %}{%- endfor -%}{% if add_generation_prompt and not ns.is_tool%}{% if ns.is_last_user or ns.is_only_sys or not ns.is_prefix %}{{'<|Assistant|>'}}{%- if not thinking %}{{'</think>'}}{%- else %}{{'<think>'}}{%- endif %}{% endif %}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,574 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DeepseekV32ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"aux_loss_alpha": 0.001,
|
| 8 |
+
"beta_fast": 32,
|
| 9 |
+
"beta_slow": 1,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"dim": 7168,
|
| 12 |
+
"dtype": "bfloat16",
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"ep_size": 1,
|
| 15 |
+
"first_k_dense_replace": 3,
|
| 16 |
+
"head_dim": 64,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 7168,
|
| 19 |
+
"index_head_dim": 128,
|
| 20 |
+
"index_n_heads": 64,
|
| 21 |
+
"index_top_k": 2048,
|
| 22 |
+
"index_topk": 2048,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 18432,
|
| 25 |
+
"kv_lora_rank": 512,
|
| 26 |
+
"max_batch_size": 8,
|
| 27 |
+
"max_position_embeddings": 163840,
|
| 28 |
+
"max_seq_len": 16384,
|
| 29 |
+
"mlp_bias": false,
|
| 30 |
+
"model_type": "deepseek_v32",
|
| 31 |
+
"moe_intermediate_size": 2048,
|
| 32 |
+
"moe_layer_freq": 1,
|
| 33 |
+
"mscale": 1.0,
|
| 34 |
+
"n_group": 8,
|
| 35 |
+
"n_routed_experts": 256,
|
| 36 |
+
"n_shared_experts": 1,
|
| 37 |
+
"norm_topk_prob": true,
|
| 38 |
+
"num_attention_heads": 128,
|
| 39 |
+
"num_experts_per_tok": 8,
|
| 40 |
+
"num_hidden_layers": 61,
|
| 41 |
+
"num_key_value_heads": 128,
|
| 42 |
+
"num_nextn_predict_layers": 1,
|
| 43 |
+
"original_seq_len": 4096,
|
| 44 |
+
"q_lora_rank": 1536,
|
| 45 |
+
"qk_head_dim": 192,
|
| 46 |
+
"qk_nope_head_dim": 128,
|
| 47 |
+
"qk_rope_head_dim": 64,
|
| 48 |
+
"quantization_config": {
|
| 49 |
+
"autoround_version": "0.9.5",
|
| 50 |
+
"bits": 4,
|
| 51 |
+
"data_type": "int",
|
| 52 |
+
"extra_config": {
|
| 53 |
+
"model.layers.0.self_attn.indexer.wk": {
|
| 54 |
+
"bits": 16,
|
| 55 |
+
"data_type": "float"
|
| 56 |
+
},
|
| 57 |
+
"model.layers.0.self_attn.indexer.wq_b": {
|
| 58 |
+
"bits": 16,
|
| 59 |
+
"data_type": "float"
|
| 60 |
+
},
|
| 61 |
+
"model.layers.1.self_attn.indexer.wk": {
|
| 62 |
+
"bits": 16,
|
| 63 |
+
"data_type": "float"
|
| 64 |
+
},
|
| 65 |
+
"model.layers.1.self_attn.indexer.wq_b": {
|
| 66 |
+
"bits": 16,
|
| 67 |
+
"data_type": "float"
|
| 68 |
+
},
|
| 69 |
+
"model.layers.10.self_attn.indexer.wk": {
|
| 70 |
+
"bits": 16,
|
| 71 |
+
"data_type": "float"
|
| 72 |
+
},
|
| 73 |
+
"model.layers.10.self_attn.indexer.wq_b": {
|
| 74 |
+
"bits": 16,
|
| 75 |
+
"data_type": "float"
|
| 76 |
+
},
|
| 77 |
+
"model.layers.11.self_attn.indexer.wk": {
|
| 78 |
+
"bits": 16,
|
| 79 |
+
"data_type": "float"
|
| 80 |
+
},
|
| 81 |
+
"model.layers.11.self_attn.indexer.wq_b": {
|
| 82 |
+
"bits": 16,
|
| 83 |
+
"data_type": "float"
|
| 84 |
+
},
|
| 85 |
+
"model.layers.12.self_attn.indexer.wk": {
|
| 86 |
+
"bits": 16,
|
| 87 |
+
"data_type": "float"
|
| 88 |
+
},
|
| 89 |
+
"model.layers.12.self_attn.indexer.wq_b": {
|
| 90 |
+
"bits": 16,
|
| 91 |
+
"data_type": "float"
|
| 92 |
+
},
|
| 93 |
+
"model.layers.13.self_attn.indexer.wk": {
|
| 94 |
+
"bits": 16,
|
| 95 |
+
"data_type": "float"
|
| 96 |
+
},
|
| 97 |
+
"model.layers.13.self_attn.indexer.wq_b": {
|
| 98 |
+
"bits": 16,
|
| 99 |
+
"data_type": "float"
|
| 100 |
+
},
|
| 101 |
+
"model.layers.14.self_attn.indexer.wk": {
|
| 102 |
+
"bits": 16,
|
| 103 |
+
"data_type": "float"
|
| 104 |
+
},
|
| 105 |
+
"model.layers.14.self_attn.indexer.wq_b": {
|
| 106 |
+
"bits": 16,
|
| 107 |
+
"data_type": "float"
|
| 108 |
+
},
|
| 109 |
+
"model.layers.15.self_attn.indexer.wk": {
|
| 110 |
+
"bits": 16,
|
| 111 |
+
"data_type": "float"
|
| 112 |
+
},
|
| 113 |
+
"model.layers.15.self_attn.indexer.wq_b": {
|
| 114 |
+
"bits": 16,
|
| 115 |
+
"data_type": "float"
|
| 116 |
+
},
|
| 117 |
+
"model.layers.16.self_attn.indexer.wk": {
|
| 118 |
+
"bits": 16,
|
| 119 |
+
"data_type": "float"
|
| 120 |
+
},
|
| 121 |
+
"model.layers.16.self_attn.indexer.wq_b": {
|
| 122 |
+
"bits": 16,
|
| 123 |
+
"data_type": "float"
|
| 124 |
+
},
|
| 125 |
+
"model.layers.17.self_attn.indexer.wk": {
|
| 126 |
+
"bits": 16,
|
| 127 |
+
"data_type": "float"
|
| 128 |
+
},
|
| 129 |
+
"model.layers.17.self_attn.indexer.wq_b": {
|
| 130 |
+
"bits": 16,
|
| 131 |
+
"data_type": "float"
|
| 132 |
+
},
|
| 133 |
+
"model.layers.18.self_attn.indexer.wk": {
|
| 134 |
+
"bits": 16,
|
| 135 |
+
"data_type": "float"
|
| 136 |
+
},
|
| 137 |
+
"model.layers.18.self_attn.indexer.wq_b": {
|
| 138 |
+
"bits": 16,
|
| 139 |
+
"data_type": "float"
|
| 140 |
+
},
|
| 141 |
+
"model.layers.19.self_attn.indexer.wk": {
|
| 142 |
+
"bits": 16,
|
| 143 |
+
"data_type": "float"
|
| 144 |
+
},
|
| 145 |
+
"model.layers.19.self_attn.indexer.wq_b": {
|
| 146 |
+
"bits": 16,
|
| 147 |
+
"data_type": "float"
|
| 148 |
+
},
|
| 149 |
+
"model.layers.2.self_attn.indexer.wk": {
|
| 150 |
+
"bits": 16,
|
| 151 |
+
"data_type": "float"
|
| 152 |
+
},
|
| 153 |
+
"model.layers.2.self_attn.indexer.wq_b": {
|
| 154 |
+
"bits": 16,
|
| 155 |
+
"data_type": "float"
|
| 156 |
+
},
|
| 157 |
+
"model.layers.20.self_attn.indexer.wk": {
|
| 158 |
+
"bits": 16,
|
| 159 |
+
"data_type": "float"
|
| 160 |
+
},
|
| 161 |
+
"model.layers.20.self_attn.indexer.wq_b": {
|
| 162 |
+
"bits": 16,
|
| 163 |
+
"data_type": "float"
|
| 164 |
+
},
|
| 165 |
+
"model.layers.21.self_attn.indexer.wk": {
|
| 166 |
+
"bits": 16,
|
| 167 |
+
"data_type": "float"
|
| 168 |
+
},
|
| 169 |
+
"model.layers.21.self_attn.indexer.wq_b": {
|
| 170 |
+
"bits": 16,
|
| 171 |
+
"data_type": "float"
|
| 172 |
+
},
|
| 173 |
+
"model.layers.22.self_attn.indexer.wk": {
|
| 174 |
+
"bits": 16,
|
| 175 |
+
"data_type": "float"
|
| 176 |
+
},
|
| 177 |
+
"model.layers.22.self_attn.indexer.wq_b": {
|
| 178 |
+
"bits": 16,
|
| 179 |
+
"data_type": "float"
|
| 180 |
+
},
|
| 181 |
+
"model.layers.23.self_attn.indexer.wk": {
|
| 182 |
+
"bits": 16,
|
| 183 |
+
"data_type": "float"
|
| 184 |
+
},
|
| 185 |
+
"model.layers.23.self_attn.indexer.wq_b": {
|
| 186 |
+
"bits": 16,
|
| 187 |
+
"data_type": "float"
|
| 188 |
+
},
|
| 189 |
+
"model.layers.24.self_attn.indexer.wk": {
|
| 190 |
+
"bits": 16,
|
| 191 |
+
"data_type": "float"
|
| 192 |
+
},
|
| 193 |
+
"model.layers.24.self_attn.indexer.wq_b": {
|
| 194 |
+
"bits": 16,
|
| 195 |
+
"data_type": "float"
|
| 196 |
+
},
|
| 197 |
+
"model.layers.25.self_attn.indexer.wk": {
|
| 198 |
+
"bits": 16,
|
| 199 |
+
"data_type": "float"
|
| 200 |
+
},
|
| 201 |
+
"model.layers.25.self_attn.indexer.wq_b": {
|
| 202 |
+
"bits": 16,
|
| 203 |
+
"data_type": "float"
|
| 204 |
+
},
|
| 205 |
+
"model.layers.26.self_attn.indexer.wk": {
|
| 206 |
+
"bits": 16,
|
| 207 |
+
"data_type": "float"
|
| 208 |
+
},
|
| 209 |
+
"model.layers.26.self_attn.indexer.wq_b": {
|
| 210 |
+
"bits": 16,
|
| 211 |
+
"data_type": "float"
|
| 212 |
+
},
|
| 213 |
+
"model.layers.27.self_attn.indexer.wk": {
|
| 214 |
+
"bits": 16,
|
| 215 |
+
"data_type": "float"
|
| 216 |
+
},
|
| 217 |
+
"model.layers.27.self_attn.indexer.wq_b": {
|
| 218 |
+
"bits": 16,
|
| 219 |
+
"data_type": "float"
|
| 220 |
+
},
|
| 221 |
+
"model.layers.28.self_attn.indexer.wk": {
|
| 222 |
+
"bits": 16,
|
| 223 |
+
"data_type": "float"
|
| 224 |
+
},
|
| 225 |
+
"model.layers.28.self_attn.indexer.wq_b": {
|
| 226 |
+
"bits": 16,
|
| 227 |
+
"data_type": "float"
|
| 228 |
+
},
|
| 229 |
+
"model.layers.29.self_attn.indexer.wk": {
|
| 230 |
+
"bits": 16,
|
| 231 |
+
"data_type": "float"
|
| 232 |
+
},
|
| 233 |
+
"model.layers.29.self_attn.indexer.wq_b": {
|
| 234 |
+
"bits": 16,
|
| 235 |
+
"data_type": "float"
|
| 236 |
+
},
|
| 237 |
+
"model.layers.3.self_attn.indexer.wk": {
|
| 238 |
+
"bits": 16,
|
| 239 |
+
"data_type": "float"
|
| 240 |
+
},
|
| 241 |
+
"model.layers.3.self_attn.indexer.wq_b": {
|
| 242 |
+
"bits": 16,
|
| 243 |
+
"data_type": "float"
|
| 244 |
+
},
|
| 245 |
+
"model.layers.30.self_attn.indexer.wk": {
|
| 246 |
+
"bits": 16,
|
| 247 |
+
"data_type": "float"
|
| 248 |
+
},
|
| 249 |
+
"model.layers.30.self_attn.indexer.wq_b": {
|
| 250 |
+
"bits": 16,
|
| 251 |
+
"data_type": "float"
|
| 252 |
+
},
|
| 253 |
+
"model.layers.31.self_attn.indexer.wk": {
|
| 254 |
+
"bits": 16,
|
| 255 |
+
"data_type": "float"
|
| 256 |
+
},
|
| 257 |
+
"model.layers.31.self_attn.indexer.wq_b": {
|
| 258 |
+
"bits": 16,
|
| 259 |
+
"data_type": "float"
|
| 260 |
+
},
|
| 261 |
+
"model.layers.32.self_attn.indexer.wk": {
|
| 262 |
+
"bits": 16,
|
| 263 |
+
"data_type": "float"
|
| 264 |
+
},
|
| 265 |
+
"model.layers.32.self_attn.indexer.wq_b": {
|
| 266 |
+
"bits": 16,
|
| 267 |
+
"data_type": "float"
|
| 268 |
+
},
|
| 269 |
+
"model.layers.33.self_attn.indexer.wk": {
|
| 270 |
+
"bits": 16,
|
| 271 |
+
"data_type": "float"
|
| 272 |
+
},
|
| 273 |
+
"model.layers.33.self_attn.indexer.wq_b": {
|
| 274 |
+
"bits": 16,
|
| 275 |
+
"data_type": "float"
|
| 276 |
+
},
|
| 277 |
+
"model.layers.34.self_attn.indexer.wk": {
|
| 278 |
+
"bits": 16,
|
| 279 |
+
"data_type": "float"
|
| 280 |
+
},
|
| 281 |
+
"model.layers.34.self_attn.indexer.wq_b": {
|
| 282 |
+
"bits": 16,
|
| 283 |
+
"data_type": "float"
|
| 284 |
+
},
|
| 285 |
+
"model.layers.35.self_attn.indexer.wk": {
|
| 286 |
+
"bits": 16,
|
| 287 |
+
"data_type": "float"
|
| 288 |
+
},
|
| 289 |
+
"model.layers.35.self_attn.indexer.wq_b": {
|
| 290 |
+
"bits": 16,
|
| 291 |
+
"data_type": "float"
|
| 292 |
+
},
|
| 293 |
+
"model.layers.36.self_attn.indexer.wk": {
|
| 294 |
+
"bits": 16,
|
| 295 |
+
"data_type": "float"
|
| 296 |
+
},
|
| 297 |
+
"model.layers.36.self_attn.indexer.wq_b": {
|
| 298 |
+
"bits": 16,
|
| 299 |
+
"data_type": "float"
|
| 300 |
+
},
|
| 301 |
+
"model.layers.37.self_attn.indexer.wk": {
|
| 302 |
+
"bits": 16,
|
| 303 |
+
"data_type": "float"
|
| 304 |
+
},
|
| 305 |
+
"model.layers.37.self_attn.indexer.wq_b": {
|
| 306 |
+
"bits": 16,
|
| 307 |
+
"data_type": "float"
|
| 308 |
+
},
|
| 309 |
+
"model.layers.38.self_attn.indexer.wk": {
|
| 310 |
+
"bits": 16,
|
| 311 |
+
"data_type": "float"
|
| 312 |
+
},
|
| 313 |
+
"model.layers.38.self_attn.indexer.wq_b": {
|
| 314 |
+
"bits": 16,
|
| 315 |
+
"data_type": "float"
|
| 316 |
+
},
|
| 317 |
+
"model.layers.39.self_attn.indexer.wk": {
|
| 318 |
+
"bits": 16,
|
| 319 |
+
"data_type": "float"
|
| 320 |
+
},
|
| 321 |
+
"model.layers.39.self_attn.indexer.wq_b": {
|
| 322 |
+
"bits": 16,
|
| 323 |
+
"data_type": "float"
|
| 324 |
+
},
|
| 325 |
+
"model.layers.4.self_attn.indexer.wk": {
|
| 326 |
+
"bits": 16,
|
| 327 |
+
"data_type": "float"
|
| 328 |
+
},
|
| 329 |
+
"model.layers.4.self_attn.indexer.wq_b": {
|
| 330 |
+
"bits": 16,
|
| 331 |
+
"data_type": "float"
|
| 332 |
+
},
|
| 333 |
+
"model.layers.40.self_attn.indexer.wk": {
|
| 334 |
+
"bits": 16,
|
| 335 |
+
"data_type": "float"
|
| 336 |
+
},
|
| 337 |
+
"model.layers.40.self_attn.indexer.wq_b": {
|
| 338 |
+
"bits": 16,
|
| 339 |
+
"data_type": "float"
|
| 340 |
+
},
|
| 341 |
+
"model.layers.41.self_attn.indexer.wk": {
|
| 342 |
+
"bits": 16,
|
| 343 |
+
"data_type": "float"
|
| 344 |
+
},
|
| 345 |
+
"model.layers.41.self_attn.indexer.wq_b": {
|
| 346 |
+
"bits": 16,
|
| 347 |
+
"data_type": "float"
|
| 348 |
+
},
|
| 349 |
+
"model.layers.42.self_attn.indexer.wk": {
|
| 350 |
+
"bits": 16,
|
| 351 |
+
"data_type": "float"
|
| 352 |
+
},
|
| 353 |
+
"model.layers.42.self_attn.indexer.wq_b": {
|
| 354 |
+
"bits": 16,
|
| 355 |
+
"data_type": "float"
|
| 356 |
+
},
|
| 357 |
+
"model.layers.43.self_attn.indexer.wk": {
|
| 358 |
+
"bits": 16,
|
| 359 |
+
"data_type": "float"
|
| 360 |
+
},
|
| 361 |
+
"model.layers.43.self_attn.indexer.wq_b": {
|
| 362 |
+
"bits": 16,
|
| 363 |
+
"data_type": "float"
|
| 364 |
+
},
|
| 365 |
+
"model.layers.44.self_attn.indexer.wk": {
|
| 366 |
+
"bits": 16,
|
| 367 |
+
"data_type": "float"
|
| 368 |
+
},
|
| 369 |
+
"model.layers.44.self_attn.indexer.wq_b": {
|
| 370 |
+
"bits": 16,
|
| 371 |
+
"data_type": "float"
|
| 372 |
+
},
|
| 373 |
+
"model.layers.45.self_attn.indexer.wk": {
|
| 374 |
+
"bits": 16,
|
| 375 |
+
"data_type": "float"
|
| 376 |
+
},
|
| 377 |
+
"model.layers.45.self_attn.indexer.wq_b": {
|
| 378 |
+
"bits": 16,
|
| 379 |
+
"data_type": "float"
|
| 380 |
+
},
|
| 381 |
+
"model.layers.46.self_attn.indexer.wk": {
|
| 382 |
+
"bits": 16,
|
| 383 |
+
"data_type": "float"
|
| 384 |
+
},
|
| 385 |
+
"model.layers.46.self_attn.indexer.wq_b": {
|
| 386 |
+
"bits": 16,
|
| 387 |
+
"data_type": "float"
|
| 388 |
+
},
|
| 389 |
+
"model.layers.47.self_attn.indexer.wk": {
|
| 390 |
+
"bits": 16,
|
| 391 |
+
"data_type": "float"
|
| 392 |
+
},
|
| 393 |
+
"model.layers.47.self_attn.indexer.wq_b": {
|
| 394 |
+
"bits": 16,
|
| 395 |
+
"data_type": "float"
|
| 396 |
+
},
|
| 397 |
+
"model.layers.48.self_attn.indexer.wk": {
|
| 398 |
+
"bits": 16,
|
| 399 |
+
"data_type": "float"
|
| 400 |
+
},
|
| 401 |
+
"model.layers.48.self_attn.indexer.wq_b": {
|
| 402 |
+
"bits": 16,
|
| 403 |
+
"data_type": "float"
|
| 404 |
+
},
|
| 405 |
+
"model.layers.49.self_attn.indexer.wk": {
|
| 406 |
+
"bits": 16,
|
| 407 |
+
"data_type": "float"
|
| 408 |
+
},
|
| 409 |
+
"model.layers.49.self_attn.indexer.wq_b": {
|
| 410 |
+
"bits": 16,
|
| 411 |
+
"data_type": "float"
|
| 412 |
+
},
|
| 413 |
+
"model.layers.5.self_attn.indexer.wk": {
|
| 414 |
+
"bits": 16,
|
| 415 |
+
"data_type": "float"
|
| 416 |
+
},
|
| 417 |
+
"model.layers.5.self_attn.indexer.wq_b": {
|
| 418 |
+
"bits": 16,
|
| 419 |
+
"data_type": "float"
|
| 420 |
+
},
|
| 421 |
+
"model.layers.50.self_attn.indexer.wk": {
|
| 422 |
+
"bits": 16,
|
| 423 |
+
"data_type": "float"
|
| 424 |
+
},
|
| 425 |
+
"model.layers.50.self_attn.indexer.wq_b": {
|
| 426 |
+
"bits": 16,
|
| 427 |
+
"data_type": "float"
|
| 428 |
+
},
|
| 429 |
+
"model.layers.51.self_attn.indexer.wk": {
|
| 430 |
+
"bits": 16,
|
| 431 |
+
"data_type": "float"
|
| 432 |
+
},
|
| 433 |
+
"model.layers.51.self_attn.indexer.wq_b": {
|
| 434 |
+
"bits": 16,
|
| 435 |
+
"data_type": "float"
|
| 436 |
+
},
|
| 437 |
+
"model.layers.52.self_attn.indexer.wk": {
|
| 438 |
+
"bits": 16,
|
| 439 |
+
"data_type": "float"
|
| 440 |
+
},
|
| 441 |
+
"model.layers.52.self_attn.indexer.wq_b": {
|
| 442 |
+
"bits": 16,
|
| 443 |
+
"data_type": "float"
|
| 444 |
+
},
|
| 445 |
+
"model.layers.53.self_attn.indexer.wk": {
|
| 446 |
+
"bits": 16,
|
| 447 |
+
"data_type": "float"
|
| 448 |
+
},
|
| 449 |
+
"model.layers.53.self_attn.indexer.wq_b": {
|
| 450 |
+
"bits": 16,
|
| 451 |
+
"data_type": "float"
|
| 452 |
+
},
|
| 453 |
+
"model.layers.54.self_attn.indexer.wk": {
|
| 454 |
+
"bits": 16,
|
| 455 |
+
"data_type": "float"
|
| 456 |
+
},
|
| 457 |
+
"model.layers.54.self_attn.indexer.wq_b": {
|
| 458 |
+
"bits": 16,
|
| 459 |
+
"data_type": "float"
|
| 460 |
+
},
|
| 461 |
+
"model.layers.55.self_attn.indexer.wk": {
|
| 462 |
+
"bits": 16,
|
| 463 |
+
"data_type": "float"
|
| 464 |
+
},
|
| 465 |
+
"model.layers.55.self_attn.indexer.wq_b": {
|
| 466 |
+
"bits": 16,
|
| 467 |
+
"data_type": "float"
|
| 468 |
+
},
|
| 469 |
+
"model.layers.56.self_attn.indexer.wk": {
|
| 470 |
+
"bits": 16,
|
| 471 |
+
"data_type": "float"
|
| 472 |
+
},
|
| 473 |
+
"model.layers.56.self_attn.indexer.wq_b": {
|
| 474 |
+
"bits": 16,
|
| 475 |
+
"data_type": "float"
|
| 476 |
+
},
|
| 477 |
+
"model.layers.57.self_attn.indexer.wk": {
|
| 478 |
+
"bits": 16,
|
| 479 |
+
"data_type": "float"
|
| 480 |
+
},
|
| 481 |
+
"model.layers.57.self_attn.indexer.wq_b": {
|
| 482 |
+
"bits": 16,
|
| 483 |
+
"data_type": "float"
|
| 484 |
+
},
|
| 485 |
+
"model.layers.58.self_attn.indexer.wk": {
|
| 486 |
+
"bits": 16,
|
| 487 |
+
"data_type": "float"
|
| 488 |
+
},
|
| 489 |
+
"model.layers.58.self_attn.indexer.wq_b": {
|
| 490 |
+
"bits": 16,
|
| 491 |
+
"data_type": "float"
|
| 492 |
+
},
|
| 493 |
+
"model.layers.59.self_attn.indexer.wk": {
|
| 494 |
+
"bits": 16,
|
| 495 |
+
"data_type": "float"
|
| 496 |
+
},
|
| 497 |
+
"model.layers.59.self_attn.indexer.wq_b": {
|
| 498 |
+
"bits": 16,
|
| 499 |
+
"data_type": "float"
|
| 500 |
+
},
|
| 501 |
+
"model.layers.6.self_attn.indexer.wk": {
|
| 502 |
+
"bits": 16,
|
| 503 |
+
"data_type": "float"
|
| 504 |
+
},
|
| 505 |
+
"model.layers.6.self_attn.indexer.wq_b": {
|
| 506 |
+
"bits": 16,
|
| 507 |
+
"data_type": "float"
|
| 508 |
+
},
|
| 509 |
+
"model.layers.60.self_attn.indexer.wk": {
|
| 510 |
+
"bits": 16,
|
| 511 |
+
"data_type": "float"
|
| 512 |
+
},
|
| 513 |
+
"model.layers.60.self_attn.indexer.wq_b": {
|
| 514 |
+
"bits": 16,
|
| 515 |
+
"data_type": "float"
|
| 516 |
+
},
|
| 517 |
+
"model.layers.7.self_attn.indexer.wk": {
|
| 518 |
+
"bits": 16,
|
| 519 |
+
"data_type": "float"
|
| 520 |
+
},
|
| 521 |
+
"model.layers.7.self_attn.indexer.wq_b": {
|
| 522 |
+
"bits": 16,
|
| 523 |
+
"data_type": "float"
|
| 524 |
+
},
|
| 525 |
+
"model.layers.8.self_attn.indexer.wk": {
|
| 526 |
+
"bits": 16,
|
| 527 |
+
"data_type": "float"
|
| 528 |
+
},
|
| 529 |
+
"model.layers.8.self_attn.indexer.wq_b": {
|
| 530 |
+
"bits": 16,
|
| 531 |
+
"data_type": "float"
|
| 532 |
+
},
|
| 533 |
+
"model.layers.9.self_attn.indexer.wk": {
|
| 534 |
+
"bits": 16,
|
| 535 |
+
"data_type": "float"
|
| 536 |
+
},
|
| 537 |
+
"model.layers.9.self_attn.indexer.wq_b": {
|
| 538 |
+
"bits": 16,
|
| 539 |
+
"data_type": "float"
|
| 540 |
+
}
|
| 541 |
+
},
|
| 542 |
+
"group_size": 128,
|
| 543 |
+
"iters": 0,
|
| 544 |
+
"low_gpu_mem_usage": true,
|
| 545 |
+
"packing_format": "auto_round:auto_gptq",
|
| 546 |
+
"quant_method": "auto-round",
|
| 547 |
+
"sym": true
|
| 548 |
+
},
|
| 549 |
+
"rms_norm_eps": 1e-06,
|
| 550 |
+
"rope_factor": 40,
|
| 551 |
+
"rope_interleave": true,
|
| 552 |
+
"rope_scaling": {
|
| 553 |
+
"beta_fast": 32,
|
| 554 |
+
"beta_slow": 1,
|
| 555 |
+
"factor": 40,
|
| 556 |
+
"mscale": 1.0,
|
| 557 |
+
"mscale_all_dim": 1.0,
|
| 558 |
+
"original_max_position_embeddings": 4096,
|
| 559 |
+
"rope_type": "yarn",
|
| 560 |
+
"type": "yarn"
|
| 561 |
+
},
|
| 562 |
+
"rope_theta": 10000.0,
|
| 563 |
+
"routed_scaling_factor": 2.5,
|
| 564 |
+
"scale_fmt": null,
|
| 565 |
+
"scoring_func": "sigmoid",
|
| 566 |
+
"seq_aux": true,
|
| 567 |
+
"tie_word_embeddings": false,
|
| 568 |
+
"topk_group": 4,
|
| 569 |
+
"topk_method": "noaux_tc",
|
| 570 |
+
"transformers_version": "4.57.3",
|
| 571 |
+
"use_cache": true,
|
| 572 |
+
"v_head_dim": 128,
|
| 573 |
+
"vocab_size": 129280
|
| 574 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.57.3"
|
| 9 |
+
}
|
model-00001-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40f697261beacf27f8d32ef45e4de70c3450e6b2e23245eadd5c69718db937ec
|
| 3 |
+
size 4992931032
|
model-00002-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1044d5bffb0e61ad0555147338af3ae42b337921c3204b91ee064e0df3fe4d9
|
| 3 |
+
size 4994933696
|
model-00003-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f33d5925dabb9a7c1bfce03e4863943e61aae2b391bc0c6b70c6cfad06f26d09
|
| 3 |
+
size 4999807400
|
model-00004-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15ace03c9778835ac80704b9886309b054d47ef0cf74759d4f2285eec8ea2252
|
| 3 |
+
size 4998515560
|
model-00005-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11a51cad612bbde54635cc3a8861dba9431a0cec50d745e37469e8e03aff4ae4
|
| 3 |
+
size 4994933296
|
model-00006-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ced8ec80b76e048cd2a1e5f9e3be64a3f3cd993b2330cc728b12297f242c8749
|
| 3 |
+
size 4994933296
|
model-00007-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a6e3da61357d5bfd87c8ec51fcb30c150ebe0a8d3066648ef4a57c5b2fc9ace
|
| 3 |
+
size 4994933432
|
model-00008-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d64dd80b5b4fe389192da686a547855bace6bd682427399e2878931258ac5592
|
| 3 |
+
size 4994933696
|
model-00009-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f12721d01e777984ce1068b907031d57c7a39c23f12c003d4b0d7d645f62316
|
| 3 |
+
size 4982271160
|
model-00010-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4108341db0347a8c2d30a0c24180a9f9067657def90e5dc8d5a23cdab380174d
|
| 3 |
+
size 4993172368
|
model-00011-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd62bbbc8820898210fc4ed57e9fe8a000ae055bc25c5906b7e4dee86576f950
|
| 3 |
+
size 4994935240
|
model-00012-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e119dae634926848b56c458f8a818acb62a29a4e2f731693ae7f9ff81e0ec0ca
|
| 3 |
+
size 4994935240
|
model-00013-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe2e1aa0bf1ff350027d14cc49964907a49b10253b7cf591905db8dbd9467f1d
|
| 3 |
+
size 4994935408
|
model-00014-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45e1970b33d177d66c1e609abdb4352c82d6af41fcaf5aa11c98ddd0b3257e5b
|
| 3 |
+
size 4994935640
|
model-00015-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:649fcf2e7577f78b61de7bcbca80780752e189328d6d7327a0673ee5553a2590
|
| 3 |
+
size 4995764440
|
model-00016-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a505f96e69ae158be5fb1435b0f24739785f15d7358fd254865917ef8db97bfd
|
| 3 |
+
size 4994935240
|
model-00017-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf275c76e9ecc640d17fcd5bcc7c71f48a432b1bd9a11d01eb71d2703cf8cdd4
|
| 3 |
+
size 4994935240
|
model-00018-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fce20e9ca525ea317869ef349956a74778c86f2c95d5f22faecb9e78084c224
|
| 3 |
+
size 4994935240
|
model-00019-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7661f6f90dc5305f2c3489492005d3349eac39740b10c053f9354606efa7a49f
|
| 3 |
+
size 4994935432
|
model-00020-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c6f84f530a49a83d857b8997567393b1d25d24bde21084f611e41cad807267
|
| 3 |
+
size 4994935640
|
model-00021-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de2757f8e6374a4fe6560cec3f447757b86210838509313ab0f64ec30175da87
|
| 3 |
+
size 4995764408
|
model-00022-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc18a4bd5beb28cec5ebef9d1f178653391d071f85ca8062987247afd88c0e42
|
| 3 |
+
size 4994935240
|
model-00023-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05d7a092a58f2587b84e8ec37c323de5faabfe87eca6b8aea53c8dd404f285a1
|
| 3 |
+
size 4994935240
|
model-00024-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bbeb66d756dcdb1ca977f5b07ed302ec32254046689dbcc8b3e326b25dc3a2c
|
| 3 |
+
size 4994935240
|
model-00025-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20b93a5a16ec16d5d457cbf5bb68ae0609ad90473122008138783dd7a27a9efc
|
| 3 |
+
size 4994935464
|
model-00026-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1711f6b1aedaf1da877927f4182da1c6a7f822e1d03908fefb855656adb0c366
|
| 3 |
+
size 4994935640
|
model-00027-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:756a1f4576ae705a7ddf560968eaa29fe1066c34962785395e505a4b09ff53a3
|
| 3 |
+
size 4995764376
|
model-00028-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c2ba897e1492bb80851cc896bf90ed446d360f289657a88ac54d6484eb721db
|
| 3 |
+
size 4994935240
|
model-00029-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60164390983346e48c9886a696e0207f477807a6148afb543ce59cafbb7e046f
|
| 3 |
+
size 4994935240
|
model-00030-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5593dbb38b5c03194b789990d6b1fa829ef834962f40ad69b9cf7cf53a57fb59
|
| 3 |
+
size 4994935240
|
model-00031-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5df89b0a2568ba90d8e7b9426ed0582963fc5152994897d0e741d4549f7520f0
|
| 3 |
+
size 4994935504
|
model-00032-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39f78c815178cc34dc9b2fec06950cff14eb959279bb38a980e7b67c09076aaf
|
| 3 |
+
size 4994935640
|
model-00033-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c11ad37405d7d921768606fb861eee3a7a2f73f81bece874308ad0a4565f09e1
|
| 3 |
+
size 4995764352
|
model-00034-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0f0ef5ee5e23abe193738cb09c73a4b29305a642f7dbe1c11f47cf5356e1196
|
| 3 |
+
size 4994935240
|
model-00035-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14c02020872df74fe8ede9c07d97dc174de81e91db3e1e167802655ceedb0bcc
|
| 3 |
+
size 4994935240
|
model-00036-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c6f7ce8c013ba4c356748a4d7741f736310550ead532adb962f685c021b5039
|
| 3 |
+
size 4994935240
|
model-00037-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7435b723511e30bd2771e3e79a436376938db69789b8e433bda3a468ebb358b
|
| 3 |
+
size 4994935528
|
model-00038-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74bcf61ed8309f3a791a11ce10d8ad7d0ba565e8141b3ce616528b76cd63fe0d
|
| 3 |
+
size 4994935640
|
model-00039-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:086120da97d3273ac6bf37d71c974900831e9ac260b597d0581ed5660fa082e1
|
| 3 |
+
size 4995764320
|
model-00040-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0d7e6a57b9f568ae2566a8ccee013b4a639d16516cd6d76bc96c3389b3c6cb4
|
| 3 |
+
size 4994935240
|
model-00041-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7c937e984756bbeec11995c3665272bee1ca8b631d6a213461b79a0790abc8f
|
| 3 |
+
size 4994935240
|
model-00042-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1f0bf8e08519639841c795643278a5e5d3fc1b61673735ef786acff01e32fc3
|
| 3 |
+
size 4994935240
|
model-00043-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7a936ee88a22cdcbc0573477090df007ec9ac1fe2aa067c4d27da9a79411ae3
|
| 3 |
+
size 4994935552
|
model-00044-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39943ad1a4adb1e5af840dfeceb0ab951f5d3631129741a884da6f9173966084
|
| 3 |
+
size 4994935640
|
model-00045-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67f3805c09205e46e46176ce036ac1af20f93a3465325f948c5f55996e111709
|
| 3 |
+
size 4995764280
|
model-00046-of-00071.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4352137a8d03d3a44eb23d484bbbbfbf58e2f18959161dd1079310e7da4fdfa
|
| 3 |
+
size 4994935240
|