BioMistral/BioMistral-MedMNX
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: BioMistral/BioMistral-MedMNX
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-10 10:08:12 +08:00
commit ec5cacc4cb
11 changed files with 258 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
.gitattributes vendored Normal file
View File

@@ -0,0 +1,51 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

49
README.md Normal file
View File

@@ -0,0 +1,49 @@
---
license: cc-by-nc-nd-4.0
base_model:
- johnsnowlabs/JSL-MedMNX-7B
- BioMistral/BioMistral-7B-DARE
library_name: transformers
tags:
- mergekit
- merge
---
# BioMistral-MedMNX
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [johnsnowlabs/JSL-MedMNX-7B](https://huggingface.co/johnsnowlabs/JSL-MedMNX-7B) as a base.
### Models Merged
The following models were included in the merge:
* [BioMistral/BioMistral-7B-DARE](https://huggingface.co/BioMistral/BioMistral-7B-DARE)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: johnsnowlabs/JSL-MedMNX-7B
parameters:
density: 0.53
weight: 0.4
- model: BioMistral/BioMistral-7B-DARE
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
```

27
config.json Normal file
View 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": "4.39.1",
"use_cache": true,
"vocab_size": 32002
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

17
mergekit_config.yml Normal file
View File

@@ -0,0 +1,17 @@
models:
- model: johnsnowlabs/JSL-MedMNX-7B
parameters:
density: 0.53
weight: 0.4
- model: BioMistral/BioMistral-7B-DARE
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-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a719d6a433a98c52d548fcf7d72fd5dbabbd37fff607bb74551df3d0b0dae769
size 9942998080

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:01d98e0c8970d0fdc763fc440b8626d6cd25d4d252a98fecb9f1c44a5a1ba300
size 4540532728

1
model.safetensors.index.json Normal file
View File

File diff suppressed because one or more lines are too long

34
special_tokens_map.json Normal file
View 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
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95c8d7d342f6abda8ec8a81cf4e839e80198079476a5852f82aac365c8b92a84
size 1795951

69
tokenizer_config.json Normal file
View 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
}