Upload merged Qwen3-4B-Instruct-2507 model (auto-generated README)
Browse files- README.md +4 -4
- added_tokens.json +0 -4
- chat_template.jinja +26 -58
- config.json +12 -22
- generation_config.json +2 -1
- 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 +341 -400
- tokenizer.json +2 -2
- tokenizer_config.json +1 -33
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: Qwen/
|
| 3 |
datasets:
|
| 4 |
- u-10bei/dbbench_sft_dataset_react_v4
|
| 5 |
language:
|
|
@@ -18,7 +18,7 @@ tags:
|
|
| 18 |
# qwen3-4b-agent-trajectory-lora
|
| 19 |
|
| 20 |
This repository provides a **LoRA adapter** fine-tuned from
|
| 21 |
-
**Qwen/
|
| 22 |
|
| 23 |
This repository contains **LoRA adapter weights only**.
|
| 24 |
The base model must be loaded separately.
|
|
@@ -34,7 +34,7 @@ tool use, and recovery from errors.
|
|
| 34 |
|
| 35 |
## Training Configuration
|
| 36 |
|
| 37 |
-
- Base model: Qwen/
|
| 38 |
- Method: LoRA (full precision base)
|
| 39 |
- Max sequence length: 2048
|
| 40 |
- Epochs: 2
|
|
@@ -48,7 +48,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
| 48 |
from peft import PeftModel
|
| 49 |
import torch
|
| 50 |
|
| 51 |
-
base = "Qwen/
|
| 52 |
adapter = "your_id/your-repo"
|
| 53 |
|
| 54 |
tokenizer = AutoTokenizer.from_pretrained(base)
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 3 |
datasets:
|
| 4 |
- u-10bei/dbbench_sft_dataset_react_v4
|
| 5 |
language:
|
|
|
|
| 18 |
# qwen3-4b-agent-trajectory-lora
|
| 19 |
|
| 20 |
This repository provides a **LoRA adapter** fine-tuned from
|
| 21 |
+
**Qwen/Qwen2.5-7B-Instruct** using **LoRA + Unsloth**.
|
| 22 |
|
| 23 |
This repository contains **LoRA adapter weights only**.
|
| 24 |
The base model must be loaded separately.
|
|
|
|
| 34 |
|
| 35 |
## Training Configuration
|
| 36 |
|
| 37 |
+
- Base model: Qwen/Qwen2.5-7B-Instruct
|
| 38 |
- Method: LoRA (full precision base)
|
| 39 |
- Max sequence length: 2048
|
| 40 |
- Epochs: 2
|
|
|
|
| 48 |
from peft import PeftModel
|
| 49 |
import torch
|
| 50 |
|
| 51 |
+
base = "Qwen/Qwen2.5-7B-Instruct"
|
| 52 |
adapter = "your_id/your-repo"
|
| 53 |
|
| 54 |
tokenizer = AutoTokenizer.from_pretrained(base)
|
added_tokens.json
CHANGED
|
@@ -1,10 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"</think>": 151668,
|
| 3 |
"</tool_call>": 151658,
|
| 4 |
-
"</tool_response>": 151666,
|
| 5 |
-
"<think>": 151667,
|
| 6 |
"<tool_call>": 151657,
|
| 7 |
-
"<tool_response>": 151665,
|
| 8 |
"<|box_end|>": 151649,
|
| 9 |
"<|box_start|>": 151648,
|
| 10 |
"<|endoftext|>": 151643,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"</tool_call>": 151658,
|
|
|
|
|
|
|
| 3 |
"<tool_call>": 151657,
|
|
|
|
| 4 |
"<|box_end|>": 151649,
|
| 5 |
"<|box_start|>": 151648,
|
| 6 |
"<|endoftext|>": 151643,
|
chat_template.jinja
CHANGED
|
@@ -1,80 +1,48 @@
|
|
| 1 |
{%- if tools %}
|
| 2 |
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0]
|
| 4 |
-
{{- messages[0]
|
|
|
|
|
|
|
| 5 |
{%- endif %}
|
| 6 |
-
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
{%- for tool in tools %}
|
| 8 |
{{- "\n" }}
|
| 9 |
{{- tool | tojson }}
|
| 10 |
{%- endfor %}
|
| 11 |
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
{%- else %}
|
| 13 |
-
{%- if messages[0]
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0]
|
|
|
|
|
|
|
| 15 |
{%- endif %}
|
| 16 |
{%- endif %}
|
| 17 |
-
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
-
{%- for message in messages[::-1] %}
|
| 19 |
-
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
-
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
-
{%- set ns.multi_step_tool = false %}
|
| 22 |
-
{%- set ns.last_query_index = index %}
|
| 23 |
-
{%- endif %}
|
| 24 |
-
{%- endfor %}
|
| 25 |
{%- for message in messages %}
|
| 26 |
-
{%- if message.
|
| 27 |
-
{
|
| 28 |
-
{%- else %}
|
| 29 |
-
{%- set content = '' %}
|
| 30 |
-
{%- endif %}
|
| 31 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
{%- elif message.role == "assistant" %}
|
| 34 |
-
{
|
| 35 |
-
{%- if message.
|
| 36 |
-
{
|
| 37 |
-
{%- else %}
|
| 38 |
-
{%- if '</think>' in content %}
|
| 39 |
-
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
-
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
-
{%- endif %}
|
| 42 |
{%- endif %}
|
| 43 |
-
{%-
|
| 44 |
-
{%- if
|
| 45 |
-
{
|
| 46 |
-
{%- else %}
|
| 47 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
{%- endif %}
|
| 49 |
-
|
| 50 |
-
{{-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
{
|
| 54 |
-
|
| 55 |
-
{{- '\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- if tool_call.function %}
|
| 58 |
-
{%- set tool_call = tool_call.function %}
|
| 59 |
-
{%- endif %}
|
| 60 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
-
{{- tool_call.name }}
|
| 62 |
-
{{- '", "arguments": ' }}
|
| 63 |
-
{%- if tool_call.arguments is string %}
|
| 64 |
-
{{- tool_call.arguments }}
|
| 65 |
-
{%- else %}
|
| 66 |
-
{{- tool_call.arguments | tojson }}
|
| 67 |
-
{%- endif %}
|
| 68 |
-
{{- '}\n</tool_call>' }}
|
| 69 |
-
{%- endfor %}
|
| 70 |
-
{%- endif %}
|
| 71 |
{{- '<|im_end|>\n' }}
|
| 72 |
{%- elif message.role == "tool" %}
|
| 73 |
-
{%- if loop.
|
| 74 |
{{- '<|im_start|>user' }}
|
| 75 |
{%- endif %}
|
| 76 |
{{- '\n<tool_response>\n' }}
|
| 77 |
-
{{- content }}
|
| 78 |
{{- '\n</tool_response>' }}
|
| 79 |
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
{{- '<|im_end|>\n' }}
|
|
@@ -83,4 +51,4 @@
|
|
| 83 |
{%- endfor %}
|
| 84 |
{%- if add_generation_prompt %}
|
| 85 |
{{- '<|im_start|>assistant\n' }}
|
| 86 |
-
{%- endif %}
|
|
|
|
| 1 |
{%- if tools %}
|
| 2 |
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
{%- for tool in tools %}
|
| 10 |
{{- "\n" }}
|
| 11 |
{{- tool | tojson }}
|
| 12 |
{%- endfor %}
|
| 13 |
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
{%- endif %}
|
| 20 |
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
|
|
|
|
|
|
| 32 |
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
{{- '<|im_end|>\n' }}
|
| 40 |
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
{{- '<|im_start|>user' }}
|
| 43 |
{%- endif %}
|
| 44 |
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
{{- '\n</tool_response>' }}
|
| 47 |
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
{{- '<|im_end|>\n' }}
|
|
|
|
| 51 |
{%- endfor %}
|
| 52 |
{%- if add_generation_prompt %}
|
| 53 |
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
config.json
CHANGED
|
@@ -1,16 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"dtype": "bfloat16",
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
-
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
-
"hidden_size":
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size":
|
| 14 |
"layer_types": [
|
| 15 |
"full_attention",
|
| 16 |
"full_attention",
|
|
@@ -39,32 +37,24 @@
|
|
| 39 |
"full_attention",
|
| 40 |
"full_attention",
|
| 41 |
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
"full_attention"
|
| 51 |
],
|
| 52 |
-
"max_position_embeddings":
|
| 53 |
-
"max_window_layers":
|
| 54 |
-
"model_type": "
|
| 55 |
-
"num_attention_heads":
|
| 56 |
-
"num_hidden_layers":
|
| 57 |
-
"num_key_value_heads":
|
| 58 |
"pad_token_id": 151654,
|
| 59 |
"rms_norm_eps": 1e-06,
|
| 60 |
"rope_scaling": null,
|
| 61 |
-
"rope_theta":
|
| 62 |
"sliding_window": null,
|
| 63 |
-
"tie_word_embeddings":
|
| 64 |
"transformers_version": "4.56.2",
|
| 65 |
"unsloth_fixed": true,
|
| 66 |
"unsloth_version": "2025.12.7",
|
| 67 |
"use_cache": true,
|
| 68 |
"use_sliding_window": false,
|
| 69 |
-
"vocab_size":
|
| 70 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
],
|
|
|
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"dtype": "bfloat16",
|
| 7 |
"eos_token_id": 151645,
|
|
|
|
| 8 |
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 3584,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 18944,
|
| 12 |
"layer_types": [
|
| 13 |
"full_attention",
|
| 14 |
"full_attention",
|
|
|
|
| 37 |
"full_attention",
|
| 38 |
"full_attention",
|
| 39 |
"full_attention",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
"full_attention"
|
| 41 |
],
|
| 42 |
+
"max_position_embeddings": 32768,
|
| 43 |
+
"max_window_layers": 28,
|
| 44 |
+
"model_type": "qwen2",
|
| 45 |
+
"num_attention_heads": 28,
|
| 46 |
+
"num_hidden_layers": 28,
|
| 47 |
+
"num_key_value_heads": 4,
|
| 48 |
"pad_token_id": 151654,
|
| 49 |
"rms_norm_eps": 1e-06,
|
| 50 |
"rope_scaling": null,
|
| 51 |
+
"rope_theta": 1000000.0,
|
| 52 |
"sliding_window": null,
|
| 53 |
+
"tie_word_embeddings": false,
|
| 54 |
"transformers_version": "4.56.2",
|
| 55 |
"unsloth_fixed": true,
|
| 56 |
"unsloth_version": "2025.12.7",
|
| 57 |
"use_cache": true,
|
| 58 |
"use_sliding_window": false,
|
| 59 |
+
"vocab_size": 152064
|
| 60 |
}
|
generation_config.json
CHANGED
|
@@ -5,8 +5,9 @@
|
|
| 5 |
151645,
|
| 6 |
151643
|
| 7 |
],
|
| 8 |
-
"max_length":
|
| 9 |
"pad_token_id": 151654,
|
|
|
|
| 10 |
"temperature": 0.7,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.8,
|
|
|
|
| 5 |
151645,
|
| 6 |
151643
|
| 7 |
],
|
| 8 |
+
"max_length": 32768,
|
| 9 |
"pad_token_id": 151654,
|
| 10 |
+
"repetition_penalty": 1.05,
|
| 11 |
"temperature": 0.7,
|
| 12 |
"top_k": 20,
|
| 13 |
"top_p": 0.8,
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97ca73fff7cd4d814874d7c14b2aaf9684e1bbda081b992849dc6416f419b5b5
|
| 3 |
+
size 4877660776
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:449d4221a844813ecfbf2bc11028a07fc20eccdb6cd5a9ca607c6277fcc056a7
|
| 3 |
+
size 4932751008
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:256e3a06d66b209479a3b9acf09c3791e1908282bffac7b909e06f8185da99ae
|
| 3 |
+
size 4330865200
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
|
| 3 |
+
size 1089994880
|
model.safetensors.index.json
CHANGED
|
@@ -1,406 +1,347 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_parameters":
|
| 4 |
-
"total_size":
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
-
"
|
| 8 |
-
"model.
|
| 9 |
-
"model.layers.0.
|
| 10 |
-
"model.layers.0.mlp.
|
| 11 |
-
"model.layers.0.mlp.
|
| 12 |
-
"model.layers.0.
|
| 13 |
-
"model.layers.0.
|
| 14 |
-
"model.layers.0.self_attn.k_proj.
|
| 15 |
-
"model.layers.0.self_attn.
|
| 16 |
-
"model.layers.0.self_attn.
|
| 17 |
-
"model.layers.0.self_attn.q_proj.
|
| 18 |
-
"model.layers.0.self_attn.
|
| 19 |
-
"model.layers.
|
| 20 |
-
"model.layers.
|
| 21 |
-
"model.layers.1.
|
| 22 |
-
"model.layers.1.mlp.
|
| 23 |
-
"model.layers.1.
|
| 24 |
-
"model.layers.1.
|
| 25 |
-
"model.layers.1.
|
| 26 |
-
"model.layers.1.self_attn.
|
| 27 |
-
"model.layers.1.self_attn.
|
| 28 |
-
"model.layers.1.self_attn.
|
| 29 |
-
"model.layers.1.self_attn.
|
| 30 |
-
"model.layers.
|
| 31 |
-
"model.layers.
|
| 32 |
-
"model.layers.
|
| 33 |
-
"model.layers.10.
|
| 34 |
-
"model.layers.10.
|
| 35 |
-
"model.layers.10.
|
| 36 |
-
"model.layers.10.
|
| 37 |
-
"model.layers.10.
|
| 38 |
-
"model.layers.10.self_attn.
|
| 39 |
-
"model.layers.10.self_attn.
|
| 40 |
-
"model.layers.10.self_attn.
|
| 41 |
-
"model.layers.
|
| 42 |
-
"model.layers.
|
| 43 |
-
"model.layers.
|
| 44 |
-
"model.layers.
|
| 45 |
-
"model.layers.11.
|
| 46 |
-
"model.layers.11.
|
| 47 |
-
"model.layers.11.
|
| 48 |
-
"model.layers.11.
|
| 49 |
-
"model.layers.11.
|
| 50 |
-
"model.layers.11.self_attn.
|
| 51 |
-
"model.layers.11.self_attn.
|
| 52 |
-
"model.layers.
|
| 53 |
-
"model.layers.
|
| 54 |
-
"model.layers.
|
| 55 |
-
"model.layers.
|
| 56 |
-
"model.layers.
|
| 57 |
-
"model.layers.12.
|
| 58 |
-
"model.layers.12.
|
| 59 |
-
"model.layers.12.
|
| 60 |
-
"model.layers.12.
|
| 61 |
-
"model.layers.12.
|
| 62 |
-
"model.layers.12.self_attn.
|
| 63 |
-
"model.layers.
|
| 64 |
-
"model.layers.
|
| 65 |
-
"model.layers.
|
| 66 |
-
"model.layers.
|
| 67 |
-
"model.layers.
|
| 68 |
-
"model.layers.
|
| 69 |
-
"model.layers.13.
|
| 70 |
-
"model.layers.13.
|
| 71 |
-
"model.layers.13.
|
| 72 |
-
"model.layers.13.
|
| 73 |
-
"model.layers.13.
|
| 74 |
-
"model.layers.
|
| 75 |
-
"model.layers.
|
| 76 |
-
"model.layers.
|
| 77 |
-
"model.layers.
|
| 78 |
-
"model.layers.
|
| 79 |
-
"model.layers.
|
| 80 |
-
"model.layers.
|
| 81 |
-
"model.layers.14.
|
| 82 |
-
"model.layers.14.
|
| 83 |
-
"model.layers.14.
|
| 84 |
-
"model.layers.14.
|
| 85 |
-
"model.layers.
|
| 86 |
-
"model.layers.
|
| 87 |
-
"model.layers.
|
| 88 |
-
"model.layers.
|
| 89 |
-
"model.layers.
|
| 90 |
-
"model.layers.
|
| 91 |
-
"model.layers.
|
| 92 |
-
"model.layers.
|
| 93 |
-
"model.layers.15.
|
| 94 |
-
"model.layers.15.
|
| 95 |
-
"model.layers.15.
|
| 96 |
-
"model.layers.
|
| 97 |
-
"model.layers.
|
| 98 |
-
"model.layers.
|
| 99 |
-
"model.layers.
|
| 100 |
-
"model.layers.
|
| 101 |
-
"model.layers.
|
| 102 |
-
"model.layers.
|
| 103 |
-
"model.layers.
|
| 104 |
-
"model.layers.
|
| 105 |
-
"model.layers.16.
|
| 106 |
-
"model.layers.16.
|
| 107 |
-
"model.layers.
|
| 108 |
-
"model.layers.
|
| 109 |
-
"model.layers.
|
| 110 |
-
"model.layers.
|
| 111 |
-
"model.layers.
|
| 112 |
-
"model.layers.
|
| 113 |
-
"model.layers.
|
| 114 |
-
"model.layers.
|
| 115 |
-
"model.layers.
|
| 116 |
-
"model.layers.
|
| 117 |
-
"model.layers.17.
|
| 118 |
-
"model.layers.
|
| 119 |
-
"model.layers.
|
| 120 |
-
"model.layers.
|
| 121 |
-
"model.layers.
|
| 122 |
-
"model.layers.
|
| 123 |
-
"model.layers.
|
| 124 |
-
"model.layers.
|
| 125 |
-
"model.layers.
|
| 126 |
-
"model.layers.
|
| 127 |
-
"model.layers.
|
| 128 |
-
"model.layers.
|
| 129 |
-
"model.layers.
|
| 130 |
-
"model.layers.
|
| 131 |
-
"model.layers.
|
| 132 |
-
"model.layers.
|
| 133 |
-
"model.layers.
|
| 134 |
-
"model.layers.
|
| 135 |
-
"model.layers.
|
| 136 |
-
"model.layers.
|
| 137 |
-
"model.layers.
|
| 138 |
-
"model.layers.
|
| 139 |
-
"model.layers.
|
| 140 |
-
"model.layers.
|
| 141 |
-
"model.layers.
|
| 142 |
-
"model.layers.
|
| 143 |
-
"model.layers.
|
| 144 |
-
"model.layers.
|
| 145 |
-
"model.layers.
|
| 146 |
-
"model.layers.
|
| 147 |
-
"model.layers.
|
| 148 |
-
"model.layers.
|
| 149 |
-
"model.layers.
|
| 150 |
-
"model.layers.
|
| 151 |
-
"model.layers.
|
| 152 |
-
"model.layers.
|
| 153 |
-
"model.layers.
|
| 154 |
-
"model.layers.
|
| 155 |
-
"model.layers.
|
| 156 |
-
"model.layers.
|
| 157 |
-
"model.layers.
|
| 158 |
-
"model.layers.
|
| 159 |
-
"model.layers.
|
| 160 |
-
"model.layers.
|
| 161 |
-
"model.layers.
|
| 162 |
-
"model.layers.
|
| 163 |
-
"model.layers.
|
| 164 |
-
"model.layers.
|
| 165 |
-
"model.layers.
|
| 166 |
-
"model.layers.
|
| 167 |
-
"model.layers.
|
| 168 |
-
"model.layers.
|
| 169 |
-
"model.layers.
|
| 170 |
-
"model.layers.
|
| 171 |
-
"model.layers.
|
| 172 |
-
"model.layers.
|
| 173 |
-
"model.layers.
|
| 174 |
-
"model.layers.
|
| 175 |
-
"model.layers.
|
| 176 |
-
"model.layers.
|
| 177 |
-
"model.layers.
|
| 178 |
-
"model.layers.
|
| 179 |
-
"model.layers.
|
| 180 |
-
"model.layers.
|
| 181 |
-
"model.layers.
|
| 182 |
-
"model.layers.
|
| 183 |
-
"model.layers.
|
| 184 |
-
"model.layers.
|
| 185 |
-
"model.layers.
|
| 186 |
-
"model.layers.
|
| 187 |
-
"model.layers.
|
| 188 |
-
"model.layers.
|
| 189 |
-
"model.layers.
|
| 190 |
-
"model.layers.
|
| 191 |
-
"model.layers.
|
| 192 |
-
"model.layers.
|
| 193 |
-
"model.layers.
|
| 194 |
-
"model.layers.
|
| 195 |
-
"model.layers.
|
| 196 |
-
"model.layers.
|
| 197 |
-
"model.layers.
|
| 198 |
-
"model.layers.
|
| 199 |
-
"model.layers.
|
| 200 |
-
"model.layers.
|
| 201 |
-
"model.layers.
|
| 202 |
-
"model.layers.
|
| 203 |
-
"model.layers.
|
| 204 |
-
"model.layers.
|
| 205 |
-
"model.layers.
|
| 206 |
-
"model.layers.
|
| 207 |
-
"model.layers.
|
| 208 |
-
"model.layers.
|
| 209 |
-
"model.layers.
|
| 210 |
-
"model.layers.
|
| 211 |
-
"model.layers.
|
| 212 |
-
"model.layers.
|
| 213 |
-
"model.layers.
|
| 214 |
-
"model.layers.
|
| 215 |
-
"model.layers.
|
| 216 |
-
"model.layers.
|
| 217 |
-
"model.layers.
|
| 218 |
-
"model.layers.
|
| 219 |
-
"model.layers.
|
| 220 |
-
"model.layers.
|
| 221 |
-
"model.layers.
|
| 222 |
-
"model.layers.
|
| 223 |
-
"model.layers.
|
| 224 |
-
"model.layers.
|
| 225 |
-
"model.layers.
|
| 226 |
-
"model.layers.
|
| 227 |
-
"model.layers.
|
| 228 |
-
"model.layers.
|
| 229 |
-
"model.layers.
|
| 230 |
-
"model.layers.
|
| 231 |
-
"model.layers.
|
| 232 |
-
"model.layers.
|
| 233 |
-
"model.layers.
|
| 234 |
-
"model.layers.
|
| 235 |
-
"model.layers.
|
| 236 |
-
"model.layers.
|
| 237 |
-
"model.layers.
|
| 238 |
-
"model.layers.
|
| 239 |
-
"model.layers.
|
| 240 |
-
"model.layers.
|
| 241 |
-
"model.layers.
|
| 242 |
-
"model.layers.
|
| 243 |
-
"model.layers.
|
| 244 |
-
"model.layers.
|
| 245 |
-
"model.layers.
|
| 246 |
-
"model.layers.
|
| 247 |
-
"model.layers.
|
| 248 |
-
"model.layers.
|
| 249 |
-
"model.layers.
|
| 250 |
-
"model.layers.
|
| 251 |
-
"model.layers.
|
| 252 |
-
"model.layers.
|
| 253 |
-
"model.layers.
|
| 254 |
-
"model.layers.
|
| 255 |
-
"model.layers.
|
| 256 |
-
"model.layers.
|
| 257 |
-
"model.layers.
|
| 258 |
-
"model.layers.
|
| 259 |
-
"model.layers.
|
| 260 |
-
"model.layers.
|
| 261 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-
|
| 262 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-
|
| 263 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-
|
| 264 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-
|
| 265 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-
|
| 266 |
-
"model.layers.3.self_attn.
|
| 267 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-
|
| 268 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-
|
| 269 |
-
"model.layers.3.self_attn.
|
| 270 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-
|
| 271 |
-
"model.layers.3.self_attn.v_proj.
|
| 272 |
-
"model.layers.
|
| 273 |
-
"model.layers.
|
| 274 |
-
"model.layers.
|
| 275 |
-
"model.layers.
|
| 276 |
-
"model.layers.
|
| 277 |
-
"model.layers.
|
| 278 |
-
"model.layers.
|
| 279 |
-
"model.layers.
|
| 280 |
-
"model.layers.
|
| 281 |
-
"model.layers.
|
| 282 |
-
"model.layers.
|
| 283 |
-
"model.layers.
|
| 284 |
-
"model.layers.
|
| 285 |
-
"model.layers.
|
| 286 |
-
"model.layers.
|
| 287 |
-
"model.layers.
|
| 288 |
-
"model.layers.
|
| 289 |
-
"model.layers.
|
| 290 |
-
"model.layers.
|
| 291 |
-
"model.layers.
|
| 292 |
-
"model.layers.
|
| 293 |
-
"model.layers.
|
| 294 |
-
"model.layers.
|
| 295 |
-
"model.layers.
|
| 296 |
-
"model.layers.
|
| 297 |
-
"model.layers.
|
| 298 |
-
"model.layers.
|
| 299 |
-
"model.layers.
|
| 300 |
-
"model.layers.
|
| 301 |
-
"model.layers.
|
| 302 |
-
"model.layers.
|
| 303 |
-
"model.layers.
|
| 304 |
-
"model.layers.
|
| 305 |
-
"model.layers.
|
| 306 |
-
"model.layers.
|
| 307 |
-
"model.layers.
|
| 308 |
-
"model.layers.
|
| 309 |
-
"model.layers.
|
| 310 |
-
"model.layers.
|
| 311 |
-
"model.layers.
|
| 312 |
-
"model.layers.
|
| 313 |
-
"model.layers.
|
| 314 |
-
"model.layers.
|
| 315 |
-
"model.layers.
|
| 316 |
-
"model.layers.
|
| 317 |
-
"model.layers.
|
| 318 |
-
"model.layers.
|
| 319 |
-
"model.layers.
|
| 320 |
-
"model.layers.
|
| 321 |
-
"model.layers.
|
| 322 |
-
"model.layers.
|
| 323 |
-
"model.layers.
|
| 324 |
-
"model.layers.
|
| 325 |
-
"model.layers.
|
| 326 |
-
"model.layers.
|
| 327 |
-
"model.layers.
|
| 328 |
-
"model.layers.
|
| 329 |
-
"model.layers.
|
| 330 |
-
"model.layers.
|
| 331 |
-
"model.layers.
|
| 332 |
-
"model.layers.
|
| 333 |
-
"model.layers.
|
| 334 |
-
"model.layers.
|
| 335 |
-
"model.layers.
|
| 336 |
-
"model.layers.
|
| 337 |
-
"model.layers.
|
| 338 |
-
"model.layers.
|
| 339 |
-
"model.layers.
|
| 340 |
-
"model.layers.
|
| 341 |
-
"model.layers.
|
| 342 |
-
"model.layers.
|
| 343 |
-
"model.layers.
|
| 344 |
-
"model.layers.
|
| 345 |
-
"model.
|
| 346 |
-
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 354 |
-
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
-
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
-
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
-
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 376 |
-
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
-
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 383 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
-
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
-
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
-
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
-
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
-
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
-
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
-
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
-
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 405 |
}
|
| 406 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_parameters": 7615616512,
|
| 4 |
+
"total_size": 15231233024
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 289 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 296 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 297 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 298 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 299 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 300 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 301 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 308 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 309 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 310 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 311 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 312 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 313 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 320 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 321 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
| 332 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 333 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 334 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 335 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 336 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 337 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
| 344 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 345 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 346 |
}
|
| 347 |
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
CHANGED
|
@@ -177,38 +177,6 @@
|
|
| 177 |
"rstrip": false,
|
| 178 |
"single_word": false,
|
| 179 |
"special": false
|
| 180 |
-
},
|
| 181 |
-
"151665": {
|
| 182 |
-
"content": "<tool_response>",
|
| 183 |
-
"lstrip": false,
|
| 184 |
-
"normalized": false,
|
| 185 |
-
"rstrip": false,
|
| 186 |
-
"single_word": false,
|
| 187 |
-
"special": false
|
| 188 |
-
},
|
| 189 |
-
"151666": {
|
| 190 |
-
"content": "</tool_response>",
|
| 191 |
-
"lstrip": false,
|
| 192 |
-
"normalized": false,
|
| 193 |
-
"rstrip": false,
|
| 194 |
-
"single_word": false,
|
| 195 |
-
"special": false
|
| 196 |
-
},
|
| 197 |
-
"151667": {
|
| 198 |
-
"content": "<think>",
|
| 199 |
-
"lstrip": false,
|
| 200 |
-
"normalized": false,
|
| 201 |
-
"rstrip": false,
|
| 202 |
-
"single_word": false,
|
| 203 |
-
"special": false
|
| 204 |
-
},
|
| 205 |
-
"151668": {
|
| 206 |
-
"content": "</think>",
|
| 207 |
-
"lstrip": false,
|
| 208 |
-
"normalized": false,
|
| 209 |
-
"rstrip": false,
|
| 210 |
-
"single_word": false,
|
| 211 |
-
"special": false
|
| 212 |
}
|
| 213 |
},
|
| 214 |
"additional_special_tokens": [
|
|
@@ -231,7 +199,7 @@
|
|
| 231 |
"eos_token": "<|im_end|>",
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
-
"model_max_length":
|
| 235 |
"pad_token": "<|vision_pad|>",
|
| 236 |
"padding_side": "right",
|
| 237 |
"split_special_tokens": false,
|
|
|
|
| 177 |
"rstrip": false,
|
| 178 |
"single_word": false,
|
| 179 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
}
|
| 181 |
},
|
| 182 |
"additional_special_tokens": [
|
|
|
|
| 199 |
"eos_token": "<|im_end|>",
|
| 200 |
"errors": "replace",
|
| 201 |
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 32768,
|
| 203 |
"pad_token": "<|vision_pad|>",
|
| 204 |
"padding_side": "right",
|
| 205 |
"split_special_tokens": false,
|