初始化项目，由ModelHub XC社区提供模型
Model: Basher17/unsloth-granite-4.1-30b-mlx Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
37
README.md
Normal file
37
README.md
Normal file
@@ -0,0 +1,37 @@
|
||||
---
|
||||
base_model: unsloth/granite-4.1-30b
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
tags:
|
||||
- language
|
||||
- unsloth
|
||||
- granite-4.0
|
||||
- mlx
|
||||
- mlx-my-repo
|
||||
---
|
||||
|
||||
# Basher17/unsloth-granite-4.1-30b-mlx
|
||||
|
||||
The Model [Basher17/unsloth-granite-4.1-30b-mlx](https://huggingface.co/Basher17/unsloth-granite-4.1-30b-mlx) was converted to MLX format from [unsloth/granite-4.1-30b](https://huggingface.co/unsloth/granite-4.1-30b) using mlx-lm version **0.31.2**.
|
||||
|
||||
## Use with mlx
|
||||
|
||||
```bash
|
||||
pip install mlx-lm
|
||||
```
|
||||
|
||||
```python
|
||||
from mlx_lm import load, generate
|
||||
|
||||
model, tokenizer = load("Basher17/unsloth-granite-4.1-30b-mlx")
|
||||
|
||||
prompt="hello"
|
||||
|
||||
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
|
||||
messages = [{"role": "user", "content": prompt}]
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
messages, tokenize=False, add_generation_prompt=True
|
||||
)
|
||||
|
||||
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||||
```
|
||||
114
chat_template.jinja
Normal file
114
chat_template.jinja
Normal file
@@ -0,0 +1,114 @@
|
||||
{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
|
||||
{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
|
||||
{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
|
||||
{%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
|
||||
{%- if available_tools is defined and available_tools %}
|
||||
{%- set tools = available_tools %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(tools_system_message=tools_system_message_prefix,
|
||||
documents_system_message=documents_system_message_prefix,
|
||||
system_message=''
|
||||
) %}
|
||||
{%- if tools %}
|
||||
{%- for tool in tools %}
|
||||
{%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
|
||||
{%- endfor %}
|
||||
{%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
|
||||
{%- else %}
|
||||
{%- set ns.tools_system_message = '' %}
|
||||
{%- endif %}
|
||||
{%- if documents %}
|
||||
{%- for document in documents %}
|
||||
{%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
|
||||
{%- endfor %}
|
||||
{%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
|
||||
{%- else %}
|
||||
{%- set ns.documents_system_message = '' %}
|
||||
{%- endif %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- if messages[0].content is string %}
|
||||
{%- set ns.system_message = messages[0].content %}
|
||||
{%- elif messages[0].content is iterable %}
|
||||
{%- for entry in messages[0].content %}
|
||||
{%- if entry.type== 'text' %}
|
||||
{%- if ns.system_message != '' %}
|
||||
{%- set ns.system_message = ns.system_message + '\n' %}
|
||||
{%- endif %}
|
||||
{%- set ns.system_message = ns.system_message + entry.text %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{%- if tools and documents %}
|
||||
{%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
|
||||
{%- elif tools %}
|
||||
{%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
|
||||
{%- elif documents %}
|
||||
{%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{%- if tools and documents %}
|
||||
{%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
|
||||
{%- elif tools %}
|
||||
{%- set ns.system_message = ns.tools_system_message %}
|
||||
{%- elif documents %}
|
||||
{%- set ns.system_message = ns.documents_system_message %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if ns.system_message %}
|
||||
{{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- set content = namespace(val='') %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content.val = message.content %}
|
||||
{%- else %}
|
||||
{%- if message.content is iterable %}
|
||||
{%- for entry in message.content %}
|
||||
{%- if entry.type== 'text' %}
|
||||
{%- if content.val != '' %}
|
||||
{%- set content.val = content.val + '\n' %}
|
||||
{%- endif %}
|
||||
{%- set content.val = content.val + entry.text %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
|
||||
{{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
|
||||
{%- elif message.role == 'assistant' %}
|
||||
{{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content.val) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|end_of_text|>\n' }}
|
||||
{%- elif message.role == 'tool' %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
|
||||
{{- '<|start_of_role|>user<|end_of_role|>' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content.val }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
|
||||
{{- '<|end_of_text|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|start_of_role|>assistant<|end_of_role|>' }}
|
||||
{%- endif %}
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"architectures": [
|
||||
"GraniteForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attention_multiplier": 0.0078125,
|
||||
"bos_token_id": 100257,
|
||||
"embedding_multiplier": 12.0,
|
||||
"eos_token_id": 100257,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"init_method": "mup",
|
||||
"initializer_range": 0.1,
|
||||
"intermediate_size": 32768,
|
||||
"logits_scaling": 16.0,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "granite",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 64,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 100256,
|
||||
"residual_multiplier": 0.175,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 50000000,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.57.6",
|
||||
"unsloth_fixed": true,
|
||||
"use_cache": true,
|
||||
"vocab_size": 100352
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 100257,
|
||||
"eos_token_id": 100257,
|
||||
"pad_token_id": 100256,
|
||||
"transformers_version": "4.53.3"
|
||||
}
|
||||
3
model-00001-of-00011.safetensors
Normal file
3
model-00001-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a3676e171bcac9f341f9f25959cfa2a72b40fcf4a90d0b3e88fd31648021588
|
||||
size 5352019574
|
||||
3
model-00002-of-00011.safetensors
Normal file
3
model-00002-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e90982598f94a085ed07c4f31c541495e36bdf5429ef6e43c2655cca6958341b
|
||||
size 5335259209
|
||||
3
model-00003-of-00011.safetensors
Normal file
3
model-00003-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c751cdadb074968ed3d3ecc7fbfe53753fa1b8eee3f95af0898556bcd2e3ad85
|
||||
size 5335259246
|
||||
3
model-00004-of-00011.safetensors
Normal file
3
model-00004-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09e6f57240849c6205ecbc9cd29a980a01bec0ed03c6e4df774dd7af40944001
|
||||
size 5335259238
|
||||
3
model-00005-of-00011.safetensors
Normal file
3
model-00005-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:042aba176396e5f622257b0ae9d6f6a48c669bcd634fe25db51df4d4da1e29dd
|
||||
size 5335259238
|
||||
3
model-00006-of-00011.safetensors
Normal file
3
model-00006-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ea0b0daf8d7464ae47837a086a9a7c67fa6e32c9ffef6755af0cd08e0a0384d1
|
||||
size 5335259248
|
||||
3
model-00007-of-00011.safetensors
Normal file
3
model-00007-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:27661c97e559bdb1f6f825184d5773e3f81382eb4d2772c4de1ac43dca8632a1
|
||||
size 5335259244
|
||||
3
model-00008-of-00011.safetensors
Normal file
3
model-00008-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3701b6ce20b7a7cb509057d8b119ced4c5fe551785a518e6a046cd09ad53160f
|
||||
size 5335259250
|
||||
3
model-00009-of-00011.safetensors
Normal file
3
model-00009-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:93f1a8854ac4c23f18c6fb992781128987f8e4777ee1ba579cf4e456e89068ce
|
||||
size 5335259234
|
||||
3
model-00010-of-00011.safetensors
Normal file
3
model-00010-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5bb477627e599a8cc1799ce29ed48c8c6cfbc879aeba160c766f23dc11542dfc
|
||||
size 5335259240
|
||||
3
model-00011-of-00011.safetensors
Normal file
3
model-00011-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b85d6f7c30b2c5b25007b773f03ff32dc51c09b3a7fe6f78e21de6e4f3870684
|
||||
size 4362171114
|
||||
586
model.safetensors.index.json
Normal file
586
model.safetensors.index.json
Normal file
@@ -0,0 +1,586 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 57731457024,
|
||||
"total_parameters": 28865728512
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
|
||||
"model.norm.weight": "model-00011-of-00011.safetensors"
|
||||
}
|
||||
}
|
||||
501276
tokenizer.json
Normal file
501276
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
15
tokenizer_config.json
Normal file
15
tokenizer_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|end_of_text|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|end_of_text|>",
|
||||
"errors": "replace",
|
||||
"is_local": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|pad|>",
|
||||
"padding_side": "left",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"tool_parser_type": "json_tools",
|
||||
"unk_token": "<|unk|>"
|
||||
}
|
||||
Reference in New Issue
Block a user