初始化项目，由ModelHub XC社区提供模型
Model: nightmedia/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-bf16-mlx Source: Original Platform
This commit is contained in:
ModelHub XC
51
.gitattributes
vendored
Normal file
51
.gitattributes
vendored
Normal file
@@ -0,0 +1,51 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||
85
README.md
Normal file
85
README.md
Normal file
@@ -0,0 +1,85 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: DavidAU/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- merge
|
||||
- programming
|
||||
- code generation
|
||||
- code
|
||||
- coding
|
||||
- coder
|
||||
- chat
|
||||
- brainstorm
|
||||
- qwen
|
||||
- qwen3
|
||||
- qwencoder
|
||||
- brainstorm20x
|
||||
- esper
|
||||
- esper-3
|
||||
- valiant
|
||||
- valiant-labs
|
||||
- qwen-3
|
||||
- qwen-3-14b
|
||||
- 14b
|
||||
- reasoning
|
||||
- code-instruct
|
||||
- python
|
||||
- javascript
|
||||
- dev-ops
|
||||
- jenkins
|
||||
- terraform
|
||||
- scripting
|
||||
- powershell
|
||||
- azure
|
||||
- aws
|
||||
- gcp
|
||||
- cloud
|
||||
- problem-solving
|
||||
- architect
|
||||
- engineer
|
||||
- developer
|
||||
- creative
|
||||
- analytical
|
||||
- expert
|
||||
- rationality
|
||||
- conversational
|
||||
- instruct
|
||||
- float32
|
||||
- mlx
|
||||
datasets:
|
||||
- sequelbox/Titanium2.1-DeepSeek-R1
|
||||
- sequelbox/Tachibana2-DeepSeek-R1
|
||||
- sequelbox/Raiden-DeepSeek-R1
|
||||
library_name: mlx
|
||||
---
|
||||
|
||||
# Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-bf16-mlx
|
||||
|
||||
This model [Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-bf16-mlx](https://huggingface.co/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-bf16-mlx) was
|
||||
converted to MLX format from [DavidAU/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x](https://huggingface.co/DavidAU/Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x)
|
||||
using mlx-lm version **0.26.0**.
|
||||
|
||||
## Use with mlx
|
||||
|
||||
```bash
|
||||
pip install mlx-lm
|
||||
```
|
||||
|
||||
```python
|
||||
from mlx_lm import load, generate
|
||||
|
||||
model, tokenizer = load("Qwen3-Esper3-Reasoning-CODER-Instruct-21B-Brainstorm20x-bf16-mlx")
|
||||
|
||||
prompt = "hello"
|
||||
|
||||
if tokenizer.chat_template is not None:
|
||||
messages = [{"role": "user", "content": prompt}]
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
messages, add_generation_prompt=True
|
||||
)
|
||||
|
||||
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||||
```
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# 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>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\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" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set content = message.content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in message.content %}
|
||||
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 17408,
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 40,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 59,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.52.0.dev0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
3
merges.txt
Normal file
3
merges.txt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
|
||||
size 1671853
|
||||
3
model-00001-of-00008.safetensors
Normal file
3
model-00001-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d1fa848e1b78a206fa0fb554f0fdc3faefd22fd597186923ca0ecb994e882f4c
|
||||
size 5341296818
|
||||
3
model-00002-of-00008.safetensors
Normal file
3
model-00002-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:29b0108c477691412bd69cd56a35d33a5e9b557d41c68affcf1ba15778a008bb
|
||||
size 5285001137
|
||||
3
model-00003-of-00008.safetensors
Normal file
3
model-00003-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f7bdc49143732d1c5ab93a499340f88490f0ebbff5ad7b3e225d2507a7233d3
|
||||
size 5285001178
|
||||
3
model-00004-of-00008.safetensors
Normal file
3
model-00004-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ac09d77d5080572fd56b5c88b96bf4700e26e4f1cf775bd1893f76b65d93d03e
|
||||
size 5285001146
|
||||
3
model-00005-of-00008.safetensors
Normal file
3
model-00005-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5b0ad6377bfe29131597aa7397514267bcc1408e2592f2113931f3df2d9a047e
|
||||
size 5285001186
|
||||
3
model-00006-of-00008.safetensors
Normal file
3
model-00006-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c6c5ac67dbd20921e62b8973f586d89233e3504fcbe44079326f65680beca268
|
||||
size 5285001188
|
||||
3
model-00007-of-00008.safetensors
Normal file
3
model-00007-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c7694321aae3913b66222b71aabe4ea2bca17f6cf32d3e30dffcd91fddaa0e93
|
||||
size 5285001180
|
||||
3
model-00008-of-00008.safetensors
Normal file
3
model-00008-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:86e5e5020f6da10fa5755ab1ebbab928dcad211d624e558c530fe47f492717a9
|
||||
size 5037239580
|
||||
660
model.safetensors.index.json
Normal file
660
model.safetensors.index.json
Normal file
@@ -0,0 +1,660 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 42088467968,
|
||||
"total_parameters": 21044233984
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00008-of-00008.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.norm.weight": "model-00008-of-00008.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user