初始化项目，由ModelHub XC社区提供模型
Model: usermma/vintage-LLM-340m-v1-base-mlx-fp16 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
|
||||
36
README.md
Normal file
36
README.md
Normal file
@@ -0,0 +1,36 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
base_model: croqaz/vintage-LLM-340m-v1-base
|
||||
tags:
|
||||
- mlx
|
||||
---
|
||||
|
||||
# usermma/vintage-LLM-340m-v1-base-mlx-fp16
|
||||
|
||||
The Model [usermma/vintage-LLM-340m-v1-base-mlx-fp16](https://huggingface.co/usermma/vintage-LLM-340m-v1-base-mlx-fp16) was converted to MLX format from [croqaz/vintage-LLM-340m-v1-base](https://huggingface.co/croqaz/vintage-LLM-340m-v1-base) using mlx-lm version **0.31.3**.
|
||||
|
||||
## Use with mlx
|
||||
|
||||
```bash
|
||||
pip install mlx-lm
|
||||
```
|
||||
|
||||
```python
|
||||
from mlx_lm import load, generate
|
||||
|
||||
model, tokenizer = load("usermma/vintage-LLM-340m-v1-base-mlx-fp16")
|
||||
|
||||
prompt = "hello"
|
||||
|
||||
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
|
||||
messages = [{"role": "user", "content": prompt}]
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
messages, tokenize=False, add_generation_prompt=True
|
||||
)
|
||||
|
||||
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||||
```
|
||||
7
chat_template.jinja
Normal file
7
chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
||||
{%- for message in messages %}
|
||||
{{- bos_token + '<|' + message['role'] + '|>\n' + message['content'].strip() + eos_token + '\n'}}
|
||||
{% endfor -%}
|
||||
|
||||
{%- if add_generation_prompt %}
|
||||
{{- bos_token + '<|assistant|>\n'}}
|
||||
{% endif -%}
|
||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 3,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": [
|
||||
4,
|
||||
2
|
||||
],
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"max_position_embeddings": 65536,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 18,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"factor": 16.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 4096,
|
||||
"rope_theta": 10000.0,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.10.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 3,
|
||||
"eos_token_id": [
|
||||
4,
|
||||
2
|
||||
],
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "5.10.2",
|
||||
"use_cache": false
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e0a6e49cd85f49c66224cc18ec63a526581be8a1bd21ebcb2938b000ea200e5b
|
||||
size 681668724
|
||||
173
model.safetensors.index.json
Normal file
173
model.safetensors.index.json
Normal file
@@ -0,0 +1,173 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 681650176,
|
||||
"total_parameters": 340825088
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model.safetensors",
|
||||
"model.embed_tokens.weight": "model.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.norm.weight": "model.safetensors"
|
||||
}
|
||||
}
|
||||
163080
tokenizer.json
Normal file
163080
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
11
tokenizer_config.json
Normal file
11
tokenizer_config.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|bos|>",
|
||||
"eos_token": "<|eos|>",
|
||||
"is_local": true,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|pad|>",
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": "<|unk|>"
|
||||
}
|
||||
Reference in New Issue
Block a user