Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +2 -4
- config.json +41 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
README.md
CHANGED
@@ -8,8 +8,6 @@ tags:
|
|
8 |
- unsloth
|
9 |
- mistral
|
10 |
- trl
|
11 |
-
- merlinite
|
12 |
-
- lab
|
13 |
base_model: ibm/merlinite-7b
|
14 |
---
|
15 |
|
@@ -17,8 +15,8 @@ base_model: ibm/merlinite-7b
|
|
17 |
|
18 |
- **Developed by:** sroecker
|
19 |
- **License:** apache-2.0
|
20 |
-
- **Finetuned from model :**
|
21 |
|
22 |
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
23 |
|
24 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
8 |
- unsloth
|
9 |
- mistral
|
10 |
- trl
|
|
|
|
|
11 |
base_model: ibm/merlinite-7b
|
12 |
---
|
13 |
|
|
|
15 |
|
16 |
- **Developed by:** sroecker
|
17 |
- **License:** apache-2.0
|
18 |
+
- **Finetuned from model :** ibm/merlinite-7b
|
19 |
|
20 |
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
21 |
|
22 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ibm/merlinite-7b",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"end_token_id": 32000,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 32768,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 32001,
|
20 |
+
"quantization_config": {
|
21 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
22 |
+
"bnb_4bit_quant_type": "nf4",
|
23 |
+
"bnb_4bit_use_double_quant": true,
|
24 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
25 |
+
"llm_int8_has_fp16_weight": false,
|
26 |
+
"llm_int8_skip_modules": null,
|
27 |
+
"llm_int8_threshold": 6.0,
|
28 |
+
"load_in_4bit": true,
|
29 |
+
"load_in_8bit": false,
|
30 |
+
"quant_method": "bitsandbytes"
|
31 |
+
},
|
32 |
+
"rms_norm_eps": 1e-05,
|
33 |
+
"rope_theta": 10000.0,
|
34 |
+
"sliding_window": 4096,
|
35 |
+
"tie_word_embeddings": false,
|
36 |
+
"torch_dtype": "bfloat16",
|
37 |
+
"transformers_version": "4.38.2",
|
38 |
+
"unsloth_version": "2024.4",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 32008
|
41 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 32001,
|
6 |
+
"transformers_version": "4.38.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf82e4849883ee750f57d3702b4fb9ece314b28a5511d8540bcdbbff6b140b3b
|
3 |
+
size 4125818973
|