初始化项目，由ModelHub XC社区提供模型
Model: johnsnowlabs/JSL-MedMNX-7B-v2.0 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
69
README.md
Normal file
69
README.md
Normal file
@@ -0,0 +1,69 @@
|
||||
---
|
||||
license: cc-by-nc-nd-4.0
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- reward model
|
||||
- RLHF
|
||||
- medical
|
||||
---
|
||||
|
||||
# JSL-MedMNX-7B-v2.0
|
||||
|
||||
|
||||
[<img src="https://repository-images.githubusercontent.com/104670986/2e728700-ace4-11ea-9cfc-f3e060b25ddf">](http://www.johnsnowlabs.com)
|
||||
|
||||
|
||||
This model is developed by [John Snow Labs](https://www.johnsnowlabs.com/).
|
||||
Performance on biomedical benchmarks: [Open Medical LLM Leaderboard](https://huggingface.co/spaces/openlifescienceai/open_medical_llm_leaderboard).
|
||||
|
||||
This model is available under a [CC-BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en) license and must also conform to this [Acceptable Use Policy](https://huggingface.co/johnsnowlabs). If you need to license this model for commercial use, please contact us at info@johnsnowlabs.com.
|
||||
|
||||
## 💻 Usage
|
||||
|
||||
```python
|
||||
!pip install -qU transformers accelerate
|
||||
|
||||
from transformers import AutoTokenizer
|
||||
import transformers
|
||||
import torch
|
||||
|
||||
model = "johnsnowlabs/JSL-MedMNX-7B-v2.0"
|
||||
messages = [{"role": "user", "content": "What is a large language model?"}]
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model)
|
||||
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
pipeline = transformers.pipeline(
|
||||
"text-generation",
|
||||
model=model,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto",
|
||||
)
|
||||
|
||||
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
||||
print(outputs[0]["generated_text"])
|
||||
```
|
||||
|
||||
## 🏆 Evaluation
|
||||
|
||||
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
||||
|-------------------------------|-------|------|-----:|--------|-----:|---|-----:|
|
||||
|stem |N/A |none | 0|acc |0.6085|± |0.0057|
|
||||
| | |none | 0|acc_norm|0.5700|± |0.0067|
|
||||
| - medmcqa |Yaml |none | 0|acc |0.5625|± |0.0077|
|
||||
| | |none | 0|acc_norm|0.5625|± |0.0077|
|
||||
| - medqa_4options |Yaml |none | 0|acc |0.5947|± |0.0138|
|
||||
| | |none | 0|acc_norm|0.5947|± |0.0138|
|
||||
| - anatomy (mmlu) | 0|none | 0|acc |0.6444|± |0.0414|
|
||||
| - clinical_knowledge (mmlu) | 0|none | 0|acc |0.7509|± |0.0266|
|
||||
| - college_biology (mmlu) | 0|none | 0|acc |0.7639|± |0.0355|
|
||||
| - college_medicine (mmlu) | 0|none | 0|acc |0.6532|± |0.0363|
|
||||
| - medical_genetics (mmlu) | 0|none | 0|acc |0.7500|± |0.0435|
|
||||
| - professional_medicine (mmlu)| 0|none | 0|acc |0.7537|± |0.0262|
|
||||
| - pubmedqa | 1|none | 0|acc |0.7760|± |0.0187|
|
||||
|
||||
|Groups|Version|Filter|n-shot| Metric |Value | |Stderr|
|
||||
|------|-------|------|-----:|--------|-----:|---|-----:|
|
||||
|stem |N/A |none | 0|acc |0.6085|± |0.0057|
|
||||
| | |none | 0|acc_norm|0.5700|± |0.0067|
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "johnsnowlabs/JSL-MedMNX-7B",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 32000,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 32000,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.39.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32002
|
||||
}
|
||||
18
mergekit_config.yml
Normal file
18
mergekit_config.yml
Normal file
@@ -0,0 +1,18 @@
|
||||
|
||||
models:
|
||||
- model: johnsnowlabs/JSL-MedMNX-7B
|
||||
parameters:
|
||||
density: 0.53
|
||||
weight: 0.4
|
||||
- model: dmis-lab/meerkat-7b-v1.0
|
||||
parameters:
|
||||
density: 0.53
|
||||
weight: 0.3
|
||||
|
||||
merge_method: dare_ties
|
||||
tokenizer_source: union
|
||||
base_model: johnsnowlabs/JSL-MedMNX-7B
|
||||
parameters:
|
||||
int8_mask: true
|
||||
dtype: bfloat16
|
||||
|
||||
3
model-00001-of-00008.safetensors
Normal file
3
model-00001-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d1710c6e0342dc4c37a0370f2340556ab6fd52a9fcfff553e928e6c4504deb55
|
||||
size 1912672792
|
||||
3
model-00002-of-00008.safetensors
Normal file
3
model-00002-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3f00567b3a0867d5df3173cee002a2939192271074a3b151d6b44a7008399f8a
|
||||
size 1889603424
|
||||
3
model-00003-of-00008.safetensors
Normal file
3
model-00003-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:81c68ff37f2d2fe68761bd9073408a383a8b715bf37959bb94cda4bd59328a9a
|
||||
size 1895895360
|
||||
3
model-00004-of-00008.safetensors
Normal file
3
model-00004-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:14d3397a56de9709b96bfcae54ae14d6b8efb33aa26ffa24f0e1088f78b7cb80
|
||||
size 1946243984
|
||||
3
model-00005-of-00008.safetensors
Normal file
3
model-00005-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:33f8003cab7a07f1a779f6b86b7e32b37ad63bd1e90602a23a1361224254a826
|
||||
size 1979789776
|
||||
3
model-00006-of-00008.safetensors
Normal file
3
model-00006-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:68f55ed4b91cef741aa984cdde94a596d6b04329a5a2f77328f3cd92d3f86735
|
||||
size 1946235672
|
||||
3
model-00007-of-00008.safetensors
Normal file
3
model-00007-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6e40aaec92530ada579f0bcc6606d2c270459b399bf19fb65137be407e4d5952
|
||||
size 1923182424
|
||||
3
model-00008-of-00008.safetensors
Normal file
3
model-00008-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd6e79b50f4c10e26335313d766c80d9885256c6849ad746fe0d1eca6516c4fd
|
||||
size 989907328
|
||||
1
model.safetensors.index.json
Normal file
1
model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
34
special_tokens_map.json
Normal file
34
special_tokens_map.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|end_of_turn|>",
|
||||
"<|pad_0|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_turn|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|end_of_turn|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91152
tokenizer.json
Normal file
91152
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
69
tokenizer_config.json
Normal file
69
tokenizer_config.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32000": {
|
||||
"content": "<|end_of_turn|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|pad_0|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|end_of_turn|>",
|
||||
"<|pad_0|>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|end_of_turn|>",
|
||||
"legacy": true,
|
||||
"max_length": 1000,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<|end_of_turn|>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"stride": 0,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user