初始化项目，由ModelHub XC社区提供模型
Model: spade-rl/SPADE-Qwen3-4B-Games 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
|
||||
81
README.md
Normal file
81
README.md
Normal file
@@ -0,0 +1,81 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-4B-Instruct-2507
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- spade
|
||||
- self-play
|
||||
- reinforcement-learning
|
||||
- environment-generation
|
||||
- games
|
||||
---
|
||||
|
||||
# SPADE-Qwen3-4B-Games
|
||||
|
||||
SPADE checkpoint for the **games** setting, trained from [`Qwen/Qwen3-4B-Instruct-2507`](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507).
|
||||
|
||||
SPADE trains a single model in two roles: an **Environment Designer** that writes executable
|
||||
environments, and a **Reasoning Agent** that solves them. The Designer is rewarded for
|
||||
producing environments at the frontier of what the Agent can currently solve, so
|
||||
the curriculum keeps pace with the policy instead of being fixed in advance.
|
||||
See the [paper](https://arxiv.org/abs/2608.19197) for details.
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| Base model | [`Qwen/Qwen3-4B-Instruct-2507`](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) |
|
||||
| Setting | games |
|
||||
| Context length | 262,144 |
|
||||
|
||||
## Quickstart
|
||||
|
||||
We advise you to use the latest version of `transformers`.
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "spade-rl/SPADE-Qwen3-4B-Games"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype="auto",
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
prompt = "Give me a short introduction to large language model."
|
||||
messages = [{"role": "user", "content": prompt}]
|
||||
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||
|
||||
generated_ids = model.generate(**model_inputs, max_new_tokens=16384)
|
||||
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
|
||||
print(tokenizer.decode(output_ids, skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## Deployment
|
||||
|
||||
For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` to create an
|
||||
OpenAI-compatible API endpoint:
|
||||
|
||||
- SGLang:
|
||||
```shell
|
||||
python -m sglang.launch_server --model-path spade-rl/SPADE-Qwen3-4B-Games --context-length 262144
|
||||
```
|
||||
- vLLM:
|
||||
```shell
|
||||
vllm serve spade-rl/SPADE-Qwen3-4B-Games --max-model-len 262144
|
||||
```
|
||||
|
||||
Note: If you encounter out-of-memory (OOM) issues, consider reducing the context
|
||||
length to a shorter value, such as 32,768.
|
||||
|
||||
## Best practices
|
||||
|
||||
We recommend `temperature=0.7`, `top_p=0.8`, `top_k=20`, `min_p=0`, following
|
||||
the sampling guidance on the [base model card](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507).
|
||||
|
||||
## Related artifacts
|
||||
|
||||
- Grounding corpora: [games](https://huggingface.co/datasets/spade-rl/spade-grounding-corpus-games-15k) | [tool use](https://huggingface.co/datasets/spade-rl/spade-grounding-corpus-tooluse-15k)
|
||||
- All SPADE models, data and generated environments: [huggingface.co/spade-rl](https://huggingface.co/spade-rl)
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"max_position_embeddings": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.51.0"
|
||||
}
|
||||
3
model-00000-of-00002.safetensors
Normal file
3
model-00000-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bdbe7125406868ace3824bf80f0269f53157e2367565829d670f8aabfe74c63b
|
||||
size 5355373240
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:553824fa772bee6eac776c83f59d6faf223b2d11a4d1875b7b5f1d6c83e0cf8f
|
||||
size 2689608768
|
||||
405
model.safetensors.index.json
Normal file
405
model.safetensors.index.json
Normal file
@@ -0,0 +1,405 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 8044936192
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00000-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function 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><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 1010000,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null,
|
||||
"add_bos_token": false
|
||||
}
|
||||
Reference in New Issue
Block a user