Instructions to use sjug/DeepSeek-V3.2-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use sjug/DeepSeek-V3.2-MLX-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("sjug/DeepSeek-V3.2-MLX-4bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use sjug/DeepSeek-V3.2-MLX-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "sjug/DeepSeek-V3.2-MLX-4bit" --prompt "Once upon a time"
- Atomic Chat
Add files using upload-large-folder tool
Browse files- README.md +37 -0
- config.json +66 -0
- generation_config.json +9 -0
- model-00001-of-00088.safetensors +3 -0
- model-00002-of-00088.safetensors +3 -0
- model-00003-of-00088.safetensors +3 -0
- model-00005-of-00088.safetensors +3 -0
- model-00006-of-00088.safetensors +3 -0
- model-00009-of-00088.safetensors +3 -0
- model-00012-of-00088.safetensors +3 -0
- model-00014-of-00088.safetensors +3 -0
- model-00019-of-00088.safetensors +3 -0
- model-00020-of-00088.safetensors +3 -0
- model-00025-of-00088.safetensors +3 -0
- model-00034-of-00088.safetensors +3 -0
- model-00035-of-00088.safetensors +3 -0
- model-00037-of-00088.safetensors +3 -0
- model-00038-of-00088.safetensors +3 -0
- model-00039-of-00088.safetensors +3 -0
- model-00040-of-00088.safetensors +3 -0
- model-00041-of-00088.safetensors +3 -0
- model-00042-of-00088.safetensors +3 -0
- model-00043-of-00088.safetensors +3 -0
- model-00045-of-00088.safetensors +3 -0
- model-00046-of-00088.safetensors +3 -0
- model-00047-of-00088.safetensors +3 -0
- model-00048-of-00088.safetensors +3 -0
- model-00050-of-00088.safetensors +3 -0
- model-00053-of-00088.safetensors +3 -0
- model-00055-of-00088.safetensors +3 -0
- model-00056-of-00088.safetensors +3 -0
- model-00062-of-00088.safetensors +3 -0
- model-00064-of-00088.safetensors +3 -0
- model-00068-of-00088.safetensors +3 -0
- model-00074-of-00088.safetensors +3 -0
- model-00075-of-00088.safetensors +3 -0
- model-00076-of-00088.safetensors +3 -0
- model-00077-of-00088.safetensors +3 -0
- model-00078-of-00088.safetensors +3 -0
- model-00079-of-00088.safetensors +3 -0
- model-00080-of-00088.safetensors +3 -0
- model-00083-of-00088.safetensors +3 -0
- model-00085-of-00088.safetensors +3 -0
- model-00086-of-00088.safetensors +3 -0
- model-00087-of-00088.safetensors +3 -0
- model-00088-of-00088.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: mlx
|
| 4 |
+
base_model: deepseek-ai/DeepSeek-V3.2
|
| 5 |
+
base_model_relation: finetune
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
tags:
|
| 8 |
+
- mlx
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# sjug/DeepSeek-V3.2-MLX-4bit
|
| 12 |
+
|
| 13 |
+
This model [sjug/DeepSeek-V3.2-MLX-4bit](https://huggingface.co/sjug/DeepSeek-V3.2-MLX-4bit) was
|
| 14 |
+
converted to MLX format from [deepseek-ai/DeepSeek-V3.2](https://huggingface.co/deepseek-ai/DeepSeek-V3.2)
|
| 15 |
+
using mlx-lm version **0.28.4**.
|
| 16 |
+
|
| 17 |
+
## Use with mlx
|
| 18 |
+
|
| 19 |
+
```bash
|
| 20 |
+
pip install mlx-lm
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
+
```python
|
| 24 |
+
from mlx_lm import load, generate
|
| 25 |
+
|
| 26 |
+
model, tokenizer = load("sjug/DeepSeek-V3.2-MLX-4bit")
|
| 27 |
+
|
| 28 |
+
prompt = "hello"
|
| 29 |
+
|
| 30 |
+
if tokenizer.chat_template is not None:
|
| 31 |
+
messages = [{"role": "user", "content": prompt}]
|
| 32 |
+
prompt = tokenizer.apply_chat_template(
|
| 33 |
+
messages, add_generation_prompt=True
|
| 34 |
+
)
|
| 35 |
+
|
| 36 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 37 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DeepseekV32ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 1,
|
| 9 |
+
"ep_size": 1,
|
| 10 |
+
"first_k_dense_replace": 3,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 7168,
|
| 13 |
+
"index_head_dim": 128,
|
| 14 |
+
"index_n_heads": 64,
|
| 15 |
+
"index_topk": 2048,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 18432,
|
| 18 |
+
"kv_lora_rank": 512,
|
| 19 |
+
"max_position_embeddings": 163840,
|
| 20 |
+
"model_type": "deepseek_v32",
|
| 21 |
+
"moe_intermediate_size": 2048,
|
| 22 |
+
"moe_layer_freq": 1,
|
| 23 |
+
"n_group": 8,
|
| 24 |
+
"n_routed_experts": 256,
|
| 25 |
+
"n_shared_experts": 1,
|
| 26 |
+
"norm_topk_prob": true,
|
| 27 |
+
"num_attention_heads": 128,
|
| 28 |
+
"num_experts_per_tok": 8,
|
| 29 |
+
"num_hidden_layers": 61,
|
| 30 |
+
"num_key_value_heads": 128,
|
| 31 |
+
"num_nextn_predict_layers": 1,
|
| 32 |
+
"q_lora_rank": 1536,
|
| 33 |
+
"qk_nope_head_dim": 128,
|
| 34 |
+
"qk_rope_head_dim": 64,
|
| 35 |
+
"quantization": {
|
| 36 |
+
"group_size": 64,
|
| 37 |
+
"bits": 4,
|
| 38 |
+
"mode": "affine"
|
| 39 |
+
},
|
| 40 |
+
"quantization_config": {
|
| 41 |
+
"group_size": 64,
|
| 42 |
+
"bits": 4,
|
| 43 |
+
"mode": "affine"
|
| 44 |
+
},
|
| 45 |
+
"rms_norm_eps": 1e-06,
|
| 46 |
+
"rope_scaling": {
|
| 47 |
+
"beta_fast": 32,
|
| 48 |
+
"beta_slow": 1,
|
| 49 |
+
"factor": 40,
|
| 50 |
+
"mscale": 1.0,
|
| 51 |
+
"mscale_all_dim": 1.0,
|
| 52 |
+
"original_max_position_embeddings": 4096,
|
| 53 |
+
"type": "yarn"
|
| 54 |
+
},
|
| 55 |
+
"rope_theta": 10000,
|
| 56 |
+
"routed_scaling_factor": 2.5,
|
| 57 |
+
"scoring_func": "sigmoid",
|
| 58 |
+
"tie_word_embeddings": false,
|
| 59 |
+
"topk_group": 4,
|
| 60 |
+
"topk_method": "noaux_tc",
|
| 61 |
+
"torch_dtype": "bfloat16",
|
| 62 |
+
"transformers_version": "4.44.2",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"v_head_dim": 128,
|
| 65 |
+
"vocab_size": 129280
|
| 66 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"do_sample": true,
|
| 6 |
+
"temperature": 1.0,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.46.3"
|
| 9 |
+
}
|
model-00001-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6d4575d6637cd2ab0561e08635ebd4b44156e7c3beb5683e82b85f2d96bbbd8
|
| 3 |
+
size 3756563807
|
model-00002-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2bb22c5f22c326ba8a509e1fc57b176a63afb72812d35b13d871be80f141c01
|
| 3 |
+
size 4369439734
|
model-00003-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9e036093db3d6a6494f9cf70e7b4d5ecdcff533d15b919a9f466bdc5bb4033c
|
| 3 |
+
size 4227859222
|
model-00005-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2345e45fad9005310a9c4f45926c868be66f34f3931a41e71566db6d10d9b1a6
|
| 3 |
+
size 4369439754
|
model-00006-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59355d07bae12625f675887c6802914e90b1576c625a1dcb648bdf96c0eea015
|
| 3 |
+
size 4227859218
|
model-00009-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:821b600aa57bdb840dff411870b08879f2f942d9f23c05e1c59ac2e4313a68af
|
| 3 |
+
size 4227859222
|
model-00012-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06dbbd5a3e7fd9f9c934d4dc05da5f63ddf114ffc1943bd1e97131df08e0c88c
|
| 3 |
+
size 4227859228
|
model-00014-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bd9ec95fbf0316bcaaad153595b865948e021e426fc79cc91127d1678ba0cd1
|
| 3 |
+
size 4369439781
|
model-00019-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce81d5ccefa3b8fc871d9c80e20e8480529308c4038e0ec09ffedce251b64280
|
| 3 |
+
size 4369439875
|
model-00020-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9097737408f7f4ed68f323fec4bf81d1cbb337b1863e1ace70918784a4942c30
|
| 3 |
+
size 4369439813
|
model-00025-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3b860221ec49f29210df7e1138764692773e6ffe123507ff15f7aaaf7eba0ea
|
| 3 |
+
size 4369439915
|
model-00034-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:649d78728ca5109d60ef867f87a7d8f4283748a57d108bd83e9224d15819d694
|
| 3 |
+
size 4369439853
|
model-00035-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f03919fd47e51adaf0f64259060e607cb5e11ac8ef8577856e56225298e971a3
|
| 3 |
+
size 4369439801
|
model-00037-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb5b03a5970f92997bf711e4208a24a35eb9c179d46a754fe320c4c9a97e1bf7
|
| 3 |
+
size 4369439919
|
model-00038-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46751ad986ffe6ee9450f903e6c3d7dcf66c9fdd93d97ee3d20d600da050dff2
|
| 3 |
+
size 4369439779
|
model-00039-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e2b0fce6f61217fe1d611cb7638553549cb84bd46e8b0d38d5d6c5b09771ffd
|
| 3 |
+
size 4227859224
|
model-00040-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb82e726ef1f0a1510c8f1b4c10bd4f68f36ba3496d9bcea0396eb9cd3886bf2
|
| 3 |
+
size 4369439839
|
model-00041-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:990f67b8f7cafe8fdcf018fe5475f55f8d9fb730968fb78d84b794e6c90e1ba7
|
| 3 |
+
size 4369439779
|
model-00042-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1642ef446a629483d5b891033b6effe3b305d387418a588dadea8e5b82836a6e
|
| 3 |
+
size 4227859228
|
model-00043-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb9fde5a4527bf41a66a760d516b79f5f28cd1792b973a822caad51a287ab3ea
|
| 3 |
+
size 4369439917
|
model-00045-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94ea84645986be1414596207baf69db3346ac3fe66b5ae904f7dca496f17a1ad
|
| 3 |
+
size 4227859228
|
model-00046-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f4d97982d7b6631a47020feeca147ec400541d9366b36593109833a1bb93b1a
|
| 3 |
+
size 4369439915
|
model-00047-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a6d3cc01f5352e54f95083bbe0a47cfd0de1c101b2b5bdbdd7f59c2b90ad33c
|
| 3 |
+
size 4369439755
|
model-00048-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bdba18b86363fae03766321c369fda3d46e891ccfa058b62ea18faeb322c7d1
|
| 3 |
+
size 4227859228
|
model-00050-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72e4d0f5a5d3331d16c0350927b2dba32f1eed752e7428c8d547dd397bb9fcc3
|
| 3 |
+
size 4369439795
|
model-00053-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3850b123d6063a8234d8203293899c632394904b2eb0da869db40226654f699
|
| 3 |
+
size 4369439773
|
model-00055-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96e3dfa75e8cf275c9361ee6d2a9aee2f666acbad67bbe75611a61f90183b614
|
| 3 |
+
size 4369439851
|
model-00056-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bb160ab91e2900b6c8ad9873310c227b55b0bb9b395751dd2a9fc83a89d8da2
|
| 3 |
+
size 4369439785
|
model-00062-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3ca490b158ae6b3c872d8cccf81a24f77c139c083e3401639b1d2dad304cba1
|
| 3 |
+
size 4369439771
|
model-00064-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b67237bd4ea8cd16b1245000e9bca620637f6b840671b96aa450eb1ca9b6175c
|
| 3 |
+
size 4369439915
|
model-00068-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fd67d82fd31f1fd5a14425c748132962ed0754fc8f85f6021cea3026a985fb6
|
| 3 |
+
size 4369439761
|
model-00074-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8009731877552512bff46d33588503c69d542e3d812876acf63fa2b1e188a20e
|
| 3 |
+
size 4369439755
|
model-00075-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:268f6a3d5e9c39486d0eb356ad3ee7a426778f282944c58253f7a0a13a49abe6
|
| 3 |
+
size 4227859226
|
model-00076-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99ac7fa5074683d0c84fa5aa8e6bb56281b1fc67f6ec96ebb7ce2d79e6734f99
|
| 3 |
+
size 4369439917
|
model-00077-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9278e3007d7f996e4fc4c09f7448c53d5d26898d952b38b8018dc8e46fa59f9d
|
| 3 |
+
size 4369439777
|
model-00078-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90a1b0af992a7443e38b8156d239c4b54e8f44307309183d357b63fc849e4c58
|
| 3 |
+
size 4227859228
|
model-00079-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69df5cb69bc764698df9b28cd231878a57898e018afba2cc745c24934de7dafd
|
| 3 |
+
size 4369439865
|
model-00080-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a388d2eda885ac9174e4777ea87dac1f42bb20e38d55b28752a3e64579c20696
|
| 3 |
+
size 4369439791
|
model-00083-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d073067bf3332b479ac88f255125b1e590c8af74eb135947f4027c98ac46d146
|
| 3 |
+
size 4369439839
|
model-00085-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b70893af77b9e219fe1e2dc63b4a648e1907097772000dd9b4ededc98c4387b
|
| 3 |
+
size 4369439897
|
model-00086-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23dae9d78c52e7c01a71368ac38d07cc8dea0e267d2f9a0c36f203325a51aa66
|
| 3 |
+
size 4369439765
|
model-00087-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a6573baae6821dd0491dc2454356925b09a15124e7cf37fb578413f487fc83f
|
| 3 |
+
size 4227859226
|
model-00088-of-00088.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:694ce75eb0bda19242d451b62df4bbe512bdf622bef972fc6c3bcfa4a3bd72bf
|
| 3 |
+
size 2663675182
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end▁of▁sentence|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end▁of▁sentence|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|