初始化项目，由ModelHub XC社区提供模型
Model: alexgusevski/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-mlx 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
|
||||
37
README.md
Normal file
37
README.md
Normal file
@@ -0,0 +1,37 @@
|
||||
---
|
||||
library_name: mlx
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
- mlx
|
||||
base_model: DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# alexgusevski/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-mlx
|
||||
|
||||
This model [alexgusevski/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-mlx](https://huggingface.co/alexgusevski/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-mlx) was
|
||||
converted to MLX format from [DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B](https://huggingface.co/DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B)
|
||||
using mlx-lm version **0.30.2**.
|
||||
|
||||
## Use with mlx
|
||||
|
||||
```bash
|
||||
pip install mlx-lm
|
||||
```
|
||||
|
||||
```python
|
||||
from mlx_lm import load, generate
|
||||
|
||||
model, tokenizer = load("alexgusevski/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-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, return_dict=False,
|
||||
)
|
||||
|
||||
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||||
```
|
||||
93
chat_template.jinja
Normal file
93
chat_template.jinja
Normal file
@@ -0,0 +1,93 @@
|
||||
{{- 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 %}
|
||||
{%- if strftime_now is defined %}
|
||||
{%- set date_string = strftime_now("%d %b %Y") %}
|
||||
{%- else %}
|
||||
{%- set date_string = "26 Jul 2024" %}
|
||||
{%- endif %}
|
||||
{%- 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 #}
|
||||
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
||||
{%- if tools is not none %}
|
||||
{{- "Environment: ipython\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 %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||
{{- '"parameters": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- "}" }}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- 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 %}
|
||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 24,
|
||||
"num_hidden_layers": 67,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 32.0,
|
||||
"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": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.46.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ef3d6ab070e38a7d2449e8d2ce755e0c4b7ebc2617532a72954126400f66d2a1
|
||||
size 5368478882
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:89460afa6bc512a1da23caeb016516875523c6ff8d7daed0a158903521193858
|
||||
size 5335514466
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:75d048cfff4d99361755cb751fd00e252fa3697d4b1607057417ea7d9d8cf07e
|
||||
size 3573792749
|
||||
613
model.safetensors.index.json
Normal file
613
model.safetensors.index.json
Normal file
@@ -0,0 +1,613 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14277715968,
|
||||
"total_parameters": 7138857984
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.64.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.64.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.64.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.64.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.64.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.64.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.64.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.64.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.64.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.65.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.65.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.65.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.65.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.65.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.65.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.65.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.65.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.65.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.66.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.66.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.66.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.66.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.66.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.66.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.66.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.66.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.66.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:65ff5472d095ccd9332d9e723153d7bc7226cb6be9c1bffda738b5ba2e71bf26
|
||||
size 17210084
|
||||
19
tokenizer_config.json
Normal file
19
tokenizer_config.json
Normal file
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"additional_special_tokens": null,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|begin_of_text|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|eot_id|>",
|
||||
"is_local": true,
|
||||
"max_length": null,
|
||||
"model_input_names": [
|
||||
"input_ids",
|
||||
"attention_mask"
|
||||
],
|
||||
"model_max_length": 131072,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<|eot_id|>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "left",
|
||||
"tokenizer_class": "TokenizersBackend"
|
||||
}
|
||||
Reference in New Issue
Block a user