初始化项目，由ModelHub XC社区提供模型
Model: jamesjunyuguo/uncertain-calibrate 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
|
||||
67
README.md
Normal file
67
README.md
Normal file
@@ -0,0 +1,67 @@
|
||||
---
|
||||
license: llama3.1
|
||||
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||||
tags:
|
||||
- adaptive-rag
|
||||
- uncertainty-quantification
|
||||
- retrieval-augmented-generation
|
||||
- question-answering
|
||||
- reinforcement-learning
|
||||
- grpo
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
# uncertain-calibrate
|
||||
|
||||
Fine-tuned from `meta-llama/Llama-3.1-8B-Instruct` via **GRPO reinforcement learning** to emit a special `<uncertain>` token when the model is uncertain during reasoning, enabling uncertainty-guided adaptive retrieval.
|
||||
|
||||
## What it does
|
||||
|
||||
The model reasons step-by-step and inserts `<uncertain>` at any point where it lacks confidence in a fact. A lightweight ridge regression probe (trained on layer-13 hidden states at the `<uncertain>` span) then decides whether to trigger BM25 retrieval and a second-pass generation.
|
||||
|
||||
|
||||
## Training
|
||||
|
||||
- **Base model**: `meta-llama/Llama-3.1-8B-Instruct`
|
||||
- **Training method**: GRPO (Group Relative Policy Optimization) with EM-based reward; the model is rewarded for correct final answers, encouraging it to emit `<uncertain>` in contexts where retrieval would help
|
||||
- **Target datasets**: Multi-hop QA (HotpotQA, MuSiQue, 2WikiMultiHopQA) and open-domain QA (NQ, TriviaQA)
|
||||
|
||||
## Retrieval gating (probe)
|
||||
|
||||
A separate ridge regression probe on layer-13 hidden states over `<uncertain>` spans must be trained to use this model for adaptive RAG. The probe AUROC on held-out data is ~0.82. Use the companion probe artifact `uncertain_probe_layer13_alpha3000.pkl` from the [AdaRAGUE repository](https://github.com/JamesJunyuGuo/AdaRAGUE).
|
||||
|
||||
## Evaluation (dev_500_subsampled, 500 questions × 5 datasets, with probe gating)
|
||||
|
||||
| Dataset | EM | F1 | Trigger Rate |
|
||||
|---|---|---|---|
|
||||
| HotpotQA | 32.6 | 42.7 | 67.4% |
|
||||
| MuSiQue | 7.6 | 14.1 | 94.2% |
|
||||
| 2WikiMultiHopQA | 26.2 | 29.6 | 59.2% |
|
||||
| NQ | 31.4 | 41.0 | 52.0% |
|
||||
| TriviaQA | 56.6 | 63.2 | 34.0% |
|
||||
| **Overall** | **30.9** | **38.1** | **61.4%** |
|
||||
|
||||
Trigger rate = fraction of questions where the probe decided to retrieve.
|
||||
|
||||
## Intended use
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("your-username/uncertain-calibrate")
|
||||
model = AutoModelForCausalLM.from_pretrained("your-username/uncertain-calibrate")
|
||||
|
||||
SYSTEM = (
|
||||
"You are a helpful reasoning assistant. Think step by step. "
|
||||
"If at any point you are uncertain about a fact, emit the special token "
|
||||
"<uncertain> to signal that you need more information. "
|
||||
"End your response with 'Answer: <your answer>' on the last line."
|
||||
)
|
||||
|
||||
prompt = tokenizer.apply_chat_template([
|
||||
{"role": "system", "content": SYSTEM},
|
||||
{"role": "user", "content": "Who directed the film Interstellar?"},
|
||||
], tokenize=False, add_generation_prompt=True)
|
||||
|
||||
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128009,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 128009,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128009
|
||||
],
|
||||
"max_length": 4096,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.51.1"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6e735b1f8683f37b480b3d14be8b84ade336ef4bf7ce4d0aa6e6391f578d662a
|
||||
size 4884416864
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:959fe40ef8ae95a0de76faac59738801e3ae59e8c47eb80c41da86396e921d4d
|
||||
size 4915923992
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:60b1464d746450f660e6c6318d12797e8b8c3f7b822e24294e934c16a738b4b9
|
||||
size 4951549168
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0bb88792c6b3b15ddfd2136ba3314fc3bac2859cc21dce5ffe6a7e8979adce8c
|
||||
size 1308666376
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060522496
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00001-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
|
||||
size 17209961
|
||||
2064
tokenizer_config.json
Normal file
2064
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user