初始化项目，由ModelHub XC社区提供模型
Model: hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1 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
|
||||
51
README.md
Normal file
51
README.md
Normal file
@@ -0,0 +1,51 @@
|
||||
---
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- verl
|
||||
- math
|
||||
- grpo
|
||||
- transfer
|
||||
- llama
|
||||
- llama-3.1
|
||||
- llama-3.2
|
||||
- 8b
|
||||
- 3b
|
||||
- pool7to1
|
||||
---
|
||||
|
||||
# VERL Math Transfer Llama 3.1 8B to Llama 3.2 3B pool7to1
|
||||
|
||||
Math transfer experiment trained with verl. This repo groups all exported Hugging Face checkpoints for the Llama 3.1 8B to Llama 3.2 3B pool7to1 configuration.
|
||||
|
||||
## Layout
|
||||
|
||||
- `main`: latest exported checkpoint, currently `step-080`
|
||||
- step revisions: `step-010, step-020, step-030, step-040, step-050, step-060, step-070, step-080`
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
repo_id = "hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1"
|
||||
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(repo_id, trust_remote_code=True)
|
||||
```
|
||||
|
||||
Load a specific checkpoint revision:
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
repo_id = "hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1"
|
||||
revision = "step-080"
|
||||
tokenizer = AutoTokenizer.from_pretrained(repo_id, revision=revision, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(repo_id, revision=revision, trust_remote_code=True)
|
||||
```
|
||||
|
||||
## Notes
|
||||
|
||||
- Architecture detected from the exported config: `LlamaForCausalLM`
|
||||
- The original base model Hub ID is not encoded in these local checkpoints, so `base_model` metadata is not set automatically.
|
||||
- Checkpoints were exported from verl FSDP shards into Hugging Face `safetensors` format.
|
||||
109
chat_template.jinja
Normal file
109
chat_template.jinja
Normal file
@@ -0,0 +1,109 @@
|
||||
{{- bos_token }}
|
||||
{%- if custom_tools is defined %}
|
||||
{%- set tools = custom_tools %}
|
||||
{%- endif %}
|
||||
{%- if not tools_in_user_message is defined %}
|
||||
{%- set tools_in_user_message = true %}
|
||||
{%- endif %}
|
||||
{%- if not date_string is defined %}
|
||||
{%- set date_string = "26 Jul 2024" %}
|
||||
{%- endif %}
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = none %}
|
||||
{%- endif %}
|
||||
|
||||
{#- This block extracts the system message, so we can slot it into the right place. #}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{%- set system_message = messages[0]['content']|trim %}
|
||||
{%- set messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set system_message = "" %}
|
||||
{%- endif %}
|
||||
|
||||
{#- System message + builtin tools #}
|
||||
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
||||
{%- if builtin_tools is defined or tools is not none %}
|
||||
{{- "Environment: ipython\n" }}
|
||||
{%- endif %}
|
||||
{%- if builtin_tools is defined %}
|
||||
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
|
||||
{%- endif %}
|
||||
{{- "Cutting Knowledge Date: December 2023\n" }}
|
||||
{{- "Today Date: " + date_string + "\n\n" }}
|
||||
{%- if tools is not none and not tools_in_user_message %}
|
||||
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
||||
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||
{{- "Do not use variables.\n\n" }}
|
||||
{%- for t in tools %}
|
||||
{{- t | tojson(indent=4) }}
|
||||
{{- "\n\n" }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- system_message }}
|
||||
{{- "<|eot_id|>" }}
|
||||
|
||||
{#- Custom tools are passed in a user message with some extra guidance #}
|
||||
{%- if tools_in_user_message and not tools is none %}
|
||||
{#- Extract the first user message so we can plug it in here #}
|
||||
{%- if messages | length != 0 %}
|
||||
{%- set first_user_message = messages[0]['content']|trim %}
|
||||
{%- set messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
||||
{%- endif %}
|
||||
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
||||
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
||||
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
||||
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||
{{- "Do not use variables.\n\n" }}
|
||||
{%- for t in tools %}
|
||||
{{- t | tojson(indent=4) }}
|
||||
{{- "\n\n" }}
|
||||
{%- endfor %}
|
||||
{{- first_user_message + "<|eot_id|>"}}
|
||||
{%- endif %}
|
||||
|
||||
{%- for message in messages %}
|
||||
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
||||
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
||||
{%- elif 'tool_calls' in message %}
|
||||
{%- if not message.tool_calls|length == 1 %}
|
||||
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
||||
{%- endif %}
|
||||
{%- set tool_call = message.tool_calls[0].function %}
|
||||
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
||||
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
||||
{{- arg_name + '="' + arg_val + '"' }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- ")" }}
|
||||
{%- else %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||
{{- '"parameters": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- "}" }}
|
||||
{%- endif %}
|
||||
{%- if builtin_tools is defined %}
|
||||
{#- This means we're in ipython mode #}
|
||||
{{- "<|eom_id|>" }}
|
||||
{%- else %}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- endif %}
|
||||
{%- elif message.role == "tool" or message.role == "ipython" %}
|
||||
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
||||
{%- if message.content is mapping or message.content is iterable %}
|
||||
{{- message.content | tojson }}
|
||||
{%- else %}
|
||||
{{- message.content }}
|
||||
{%- endif %}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
||||
{%- endif %}
|
||||
36
config.json
Normal file
36
config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 128009,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 128009,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:020ffa26ef91c1aab750a6c096b2a6036a9833220fc01c9c6ddb406c9d6f5e37
|
||||
size 4957909400
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2d9371d7b546b56d909e6ffe347adadb8a28f253b30ad91a8b14f544809f55e0
|
||||
size 4917970024
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eb27eb64394bbb318aac357f8173d00d89438fe350986618a2f04f203cb91fd2
|
||||
size 4892820928
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:449d8952de7da252d135167216398c454828cc8ae623ae994b033985dd9dc058
|
||||
size 1291856032
|
||||
299
model.safetensors.index.json
Normal file
299
model.safetensors.index.json
Normal file
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8030261248,
|
||||
"total_size": 16060522496
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00001-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2063
tokenizer_config.json
Normal file
2063
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user