初始化项目，由ModelHub XC社区提供模型
Model: cognitivecomputations/Dolphin3.0-Mistral-24B 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
|
||||
24
Modelfile
Normal file
24
Modelfile
Normal file
@@ -0,0 +1,24 @@
|
||||
FROM hf.co/bartowski/cognitivecomputations_Dolphin3.0-Mistral-24B-GGUF:Q4_0
|
||||
|
||||
TEMPLATE "{{ if .System }}<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ end }}{{ if .Prompt }}<|im_start|>user
|
||||
{{ .Prompt }}<|im_end|>
|
||||
{{ end }}<|im_start|>assistant
|
||||
{{ .Response }}<|im_end|>
|
||||
"
|
||||
|
||||
SYSTEM """You are Dolphin, a lovable yet intelligent AI assistant created by Eric Hartford and his open source AI research collective, Cognitive Computations.
|
||||
Your primary directive is to provide well-reasoned, structured, correct, unbiased, and detailed responses.
|
||||
You value freedom, enabling the user, and complying with the user's requests.
|
||||
|
||||
Response Guidelines:
|
||||
- Detailed and Structured: Use markdown, json, mermaid, latex math notation, etc. when appropriate.
|
||||
- Scientific and Logical Approach: Your explanations should reflect the depth and precision of the greatest scientific minds.
|
||||
- Concise yet Complete: Ensure responses are informative, yet to the point without unnecessary elaboration.
|
||||
- Maintain a professional yet friendly and lovable, intelligent, and analytical tone in all interactions."""
|
||||
|
||||
PARAMETER num_ctx 32768
|
||||
PARAMETER temperature 0.05
|
||||
PARAMETER stop <|im_start|>
|
||||
PARAMETER stop <|im_end|>
|
||||
133
README.md
Normal file
133
README.md
Normal file
@@ -0,0 +1,133 @@
|
||||
---
|
||||
datasets:
|
||||
- OpenCoder-LLM/opc-sft-stage1
|
||||
- OpenCoder-LLM/opc-sft-stage2
|
||||
- microsoft/orca-agentinstruct-1M-v1
|
||||
- microsoft/orca-math-word-problems-200k
|
||||
- NousResearch/hermes-function-calling-v1
|
||||
- AI-MO/NuminaMath-CoT
|
||||
- AI-MO/NuminaMath-TIR
|
||||
- allenai/tulu-3-sft-mixture
|
||||
- cognitivecomputations/dolphin-coder
|
||||
- HuggingFaceTB/smoltalk
|
||||
- cognitivecomputations/samantha-data
|
||||
- m-a-p/CodeFeedback-Filtered-Instruction
|
||||
- m-a-p/Code-Feedback
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- mistralai/Mistral-Small-24B-Base-2501
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
# Dolphin 3.0 Mistral 24B 🐬
|
||||
Part of the [Dolphin 3.0 Collection](https://huggingface.co/collections/cognitivecomputations/dolphin-30-677ab47f73d7ff66743979a3)
|
||||
|
||||
Curated and trained by [Eric Hartford](https://huggingface.co/ehartford), [Ben Gitter](https://huggingface.co/bigstorm), [BlouseJury](https://huggingface.co/BlouseJury) and [Cognitive Computations](https://huggingface.co/cognitivecomputations)
|
||||
|
||||
[](https://discord.gg/cognitivecomputations)
|
||||
Discord: https://discord.gg/cognitivecomputations
|
||||
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/cNCs1TBD3FelWCJGkZ3cd.png" width="600" />
|
||||
|
||||
## Sponsors
|
||||
Our appreciation for the generous sponsors of Dolphin 3.0:
|
||||
- [Dria](https://dria.co) https://x.com/driaforall - Inference Sponsor
|
||||
- [Chutes](https://chutes.ai) https://x.com/rayon_labs - Compute Sponsor
|
||||
- [Crusoe Cloud](https://crusoe.ai/) - Compute Sponsor
|
||||
- [Andreessen Horowitz](https://a16z.com/) - provided the [grant](https://a16z.com/supporting-the-open-source-ai-community/) that originally launched Dolphin
|
||||
|
||||
## What is Dolphin?
|
||||
|
||||
Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
|
||||
|
||||
Dolphin aims to be a general purpose instruct model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products.
|
||||
1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
|
||||
2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
|
||||
3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
|
||||
4) They can see all your queries and they can potentially use that data in ways you wouldn't want.
|
||||
Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines.
|
||||
|
||||
Dolphin belongs to YOU, it is your tool, an extension of your will.
|
||||
Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin.
|
||||
|
||||
https://erichartford.com/uncensored-models
|
||||
|
||||
## Recommended Temperature
|
||||
|
||||
Experimentally we note that Mistral-24B based models require a low temperature. We have seen much better results in the range of 0.05 to 0.1.
|
||||
|
||||
## Quants
|
||||
|
||||
https://huggingface.co/bartowski/cognitivecomputations_Dolphin3.0-Mistral-24B-GGUF
|
||||
|
||||
## Run Dolphin in Ollama (13 GB)
|
||||
|
||||
```
|
||||
wget https://huggingface.co/cognitivecomputations/Dolphin3.0-Mistral-24B/resolve/main/Modelfile
|
||||
ollama create dolphin3
|
||||
ollama run dolphin3
|
||||
```
|
||||
|
||||
## Chat Template
|
||||
|
||||
We use ChatML for the chat template.
|
||||
|
||||
```
|
||||
<|im_start|>system
|
||||
You are Dolphin, a helpful AI assistant.<|im_end|>
|
||||
<|im_start|>user
|
||||
{prompt}<|im_end|>
|
||||
<|im_start|>assistant
|
||||
```
|
||||
|
||||
## System Prompt
|
||||
|
||||
In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them.
|
||||
|
||||
Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want.
|
||||
|
||||
Example use of system prompt:
|
||||
|
||||
```
|
||||
<|im_start|>system
|
||||
You are Dolphin, a golang coding assistant. you only code in golang. If the user requests any other programming language, return the solution in golang instead.<|im_end|>
|
||||
<|im_start|>user
|
||||
Please implement A* using python<|im_end|>
|
||||
<|im_start|>assistant
|
||||
```
|
||||
|
||||
## Sample Outputs
|
||||
|
||||
TBD
|
||||
|
||||
## How to use
|
||||
|
||||
There are many ways to use a huggingface model including:
|
||||
- ollama
|
||||
- LM Studio
|
||||
- Huggingface Transformers library
|
||||
- vllm
|
||||
- sglang
|
||||
- tgi
|
||||
|
||||
## Evals
|
||||
|
||||
TBD
|
||||
|
||||
## Appreciation
|
||||
|
||||
Respect and thanks to the creators of the open source datasets that were used:
|
||||
- [OpenCoder-LLM](https://huggingface.co/OpenCoder-LLM) (opc-sft-stage1, opc-sft-stage2)
|
||||
- [microsoft](https://huggingface.co/OpenCoder-LLM) (orca-agentinstruct-1M-v1, orca-math-word-problems-200k)
|
||||
- [NousResearch](https://huggingface.co/NousResearch) (hermes-function-calling-v1)
|
||||
- [AI-MO](https://huggingface.co/AI-MO) (NuminaMath-CoT, NuminaMath-TIR)
|
||||
- [allenai](https://huggingface.co/allenai) (tulu-3-sft-mixture)
|
||||
- [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) (smoltalk)
|
||||
- [m-a-p](https://huggingface.co/m-a-p) (CodeFeedback-Filtered-Instruction, Code-Feedback)
|
||||
|
||||
Special thanks to
|
||||
- Meta, Qwen, and OpenCoder, who wrote papers and published models that were instrumental in creating Dolphin 3.0.
|
||||
- [RLHFlow](https://huggingface.co/RLHFlow) for the excellent reward model used to filter the datasets
|
||||
- Deepseek, for the ridiculously fast Deepseek-V3 that we used to augment the data.
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "cognitivecomputations/Dolphin3.0-Mistral-24B",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": [2,131072],
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 32768,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 100000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.48.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131074
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [2,131072],
|
||||
"temperature": 0.05,
|
||||
"transformers_version": "4.48.1"
|
||||
}
|
||||
3
model-00001-of-00010.safetensors
Normal file
3
model-00001-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:218a7524ea7ccff7e4335683132a7f5a2a61082bc81b489a985d3d1c64e0ae20
|
||||
size 4781592216
|
||||
3
model-00002-of-00010.safetensors
Normal file
3
model-00002-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a4d6355130e05a15d44c75f29ada3fc4e8460b538a09e39beb10d342589c875b
|
||||
size 4781592784
|
||||
3
model-00003-of-00010.safetensors
Normal file
3
model-00003-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e71cbf0be43c03ed9c5fb0555c9cd64780e338b098700f65156386bcbad2c484
|
||||
size 4781592800
|
||||
3
model-00004-of-00010.safetensors
Normal file
3
model-00004-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:94ef3a5799540539d2cb161d62e34a52d809af39727c857dbd9317f0c0c29b87
|
||||
size 4886471600
|
||||
3
model-00005-of-00010.safetensors
Normal file
3
model-00005-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:211cf050607769ea0a9e62782e4e1530739f7d42f8f06f8deb0290f57b357e80
|
||||
size 4781592824
|
||||
3
model-00006-of-00010.safetensors
Normal file
3
model-00006-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2577cb910415e88302017058346d3a56cc1a7b5f2fe0ad8a43a92df774648105
|
||||
size 4781592816
|
||||
3
model-00007-of-00010.safetensors
Normal file
3
model-00007-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0af9e18f2d1e71502267d7a4f7b5737566aa0d735a176ab37a86b76920f2d549
|
||||
size 4886471600
|
||||
3
model-00008-of-00010.safetensors
Normal file
3
model-00008-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3eeea04597064f170d1436673180128d6ba5402eba132356de85b17443b855ef
|
||||
size 4781592824
|
||||
3
model-00009-of-00010.safetensors
Normal file
3
model-00009-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fb84ff22c3391477a3bdbb8701b77849e028d71b23d32c0b9730090c7b95ce5
|
||||
size 4781592816
|
||||
3
model-00010-of-00010.safetensors
Normal file
3
model-00010-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:63be31dd1f4d54a00de727ac6fe7f765a346064347fc5361a2b234781b1aedb2
|
||||
size 3900797552
|
||||
370
model.safetensors.index.json
Normal file
370
model.safetensors.index.json
Normal file
@@ -0,0 +1,370 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 47144847360
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00010-of-00010.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.norm.weight": "model-00010-of-00010.safetensors"
|
||||
}
|
||||
}
|
||||
1032
special_tokens_map.json
Normal file
1032
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d272e2518247a1d572131387580a2f6269e295616bc32dab17bbd886b55672d2
|
||||
size 17078415
|
||||
9036
tokenizer_config.json
Normal file
9036
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
7223
trainer_state.json
Normal file
7223
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user