初始化项目，由ModelHub XC社区提供模型
Model: cyLee-g/fyp-qwen Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt 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
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz 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
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl 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
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* 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
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
6
README.md
Normal file
6
README.md
Normal file
@@ -0,0 +1,6 @@
|
||||
---
|
||||
license: afl-3.0
|
||||
pipeline_tag: text-generation
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-7B-Instruct
|
||||
---
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\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>" }}
|
||||
{%- 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) 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' }}
|
||||
{%- endif %}
|
||||
61
config.json
Normal file
61
config.json
Normal file
@@ -0,0 +1,61 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "float16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.5.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
62
handler.py
Normal file
62
handler.py
Normal file
@@ -0,0 +1,62 @@
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
class EndpointHandler:
|
||||
def __init__(self, path=""):
|
||||
self.tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
|
||||
self.model = AutoModelForCausalLM.from_pretrained(
|
||||
path,
|
||||
trust_remote_code=True,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto",
|
||||
).eval()
|
||||
|
||||
def _build_prompt(self, data):
|
||||
"""
|
||||
Prefer OpenAI-style chat messages:
|
||||
{ "messages": [ {"role":"system","content":"..."}, {"role":"user","content":"..."} ] }
|
||||
|
||||
Fallback to HF-style raw inputs:
|
||||
{ "inputs": "..." }
|
||||
"""
|
||||
messages = data.get("messages", None)
|
||||
|
||||
if isinstance(messages, list) and len(messages) > 0:
|
||||
# Qwen-native formatting (matches your local_run_*.py behavior)
|
||||
return self.tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
|
||||
# fallback
|
||||
return data.get("inputs", "") or ""
|
||||
|
||||
def __call__(self, data):
|
||||
p = data.get("parameters", {}) or {}
|
||||
|
||||
max_new_tokens = int(p.get("max_new_tokens", 256))
|
||||
temperature = float(p.get("temperature", 0.7))
|
||||
top_p = float(p.get("top_p", 0.9))
|
||||
|
||||
text = self._build_prompt(data)
|
||||
|
||||
# guardrail truncation to avoid huge payloads
|
||||
text = text[:12000]
|
||||
|
||||
inputs = self.tokenizer(text, return_tensors="pt").to(self.model.device)
|
||||
do_sample = temperature > 0.0
|
||||
|
||||
gen_kwargs = dict(
|
||||
max_new_tokens=max_new_tokens,
|
||||
do_sample=do_sample,
|
||||
use_cache=True,
|
||||
)
|
||||
if do_sample:
|
||||
gen_kwargs.update(dict(temperature=temperature, top_p=top_p))
|
||||
|
||||
with torch.inference_mode():
|
||||
out = self.model.generate(**inputs, **gen_kwargs)
|
||||
|
||||
gen = out[0, inputs["input_ids"].shape[1]:]
|
||||
return [{"generated_text": self.tokenizer.decode(gen, skip_special_tokens=True).strip()}]
|
||||
3
model-00001-of-00009.safetensors
Normal file
3
model-00001-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:053d06aa9a6579967b3653c789151a7edf361899e7804c10a756b53286f602e8
|
||||
size 1089994880
|
||||
3
model-00002-of-00009.safetensors
Normal file
3
model-00002-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6a76d591099ac1f9783654fbc83f1b61a646f3303c937899978d4b645df2e47a
|
||||
size 1992867280
|
||||
3
model-00003-of-00009.safetensors
Normal file
3
model-00003-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:95811e6ddbc488a2e51ae9738bf518e89b6cdff2004d0d6c3da6fcf0037adb35
|
||||
size 1893836496
|
||||
3
model-00004-of-00009.safetensors
Normal file
3
model-00004-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fb7b3462d6d4f2d8ceab1dcce98970cf99ce2a5f20f8586cf52b362b0835cf2e
|
||||
size 1864467736
|
||||
3
model-00005-of-00009.safetensors
Normal file
3
model-00005-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e1cc3c613e90ff3a3cb68bf1c326c932c313efa440b3daf98fe89694be72d771
|
||||
size 1864467792
|
||||
3
model-00006-of-00009.safetensors
Normal file
3
model-00006-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0f0331c90fc485692e240d38196bacdb66cb143fe9e92a6be6af1eaca6a7bd3b
|
||||
size 1864467792
|
||||
3
model-00007-of-00009.safetensors
Normal file
3
model-00007-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3b7758465328d5ed12e652b9ea0bba406e0bc7573209a021ecfd7d42b11cd2a0
|
||||
size 1864467792
|
||||
3
model-00008-of-00009.safetensors
Normal file
3
model-00008-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ba210070df181fdceb376f0d7ec3c5f775c31ff455ebc984ffc3ddc1cbec7c6d
|
||||
size 1864467792
|
||||
3
model-00009-of-00009.safetensors
Normal file
3
model-00009-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:37a8de3a85009a95086d253a21749d41b80ba60b28e75b94c0fca5fefe3da649
|
||||
size 932233872
|
||||
347
model.safetensors.index.json
Normal file
347
model.safetensors.index.json
Normal file
@@ -0,0 +1,347 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 7615616512,
|
||||
"total_size": 15231233024
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00009.safetensors",
|
||||
"model.embed_tokens.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.norm.weight": "model-00009-of-00009.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
14
tokenizer_config.json
Normal file
14
tokenizer_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"is_local": false,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user