Hugging Face's logo

IQSeC-Lab
/
BinSIGHT-Dobby

GGUF
llama
llama.cpp
unsloth
conversational
Model card Files
xet
 Community
vixxi commited on
Commit
be82ef5
·
1 Parent(s): 97700dd

New trained model

Browse files
Files changed (6) hide show
  1. .gitattributes +2 -2
  2. Modelfile +1 -1
  3. README.md +6 -9
  4. config.json +31 -28
  5. llama-3-8b-instruct.Q8_0.gguf +2 -2
  6. llama-3-8b.Q8_0.gguf +0 -3
.gitattributes CHANGED
@@ -33,6 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
- llama-3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
37
  llama-3-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
38
- *.gguf filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
36
  llama-3-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
37
+ model.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
38
+ llama-3-8b-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Modelfile CHANGED
@@ -1,5 +1,5 @@
1
 
2
- FROM llama-3-8b-instruct.Q8_0.gguf
3
  TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
4
 
5
  {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
 
1
 
2
+ FROM llama-3-8b-Instruct.Q8_0.gguf
3
  TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
4
 
5
  {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
README.md CHANGED
@@ -3,24 +3,21 @@ tags:
3
  - gguf
4
  - llama.cpp
5
  - unsloth
6
- license: mit
7
  ---
8
 
9
- # BinSIGHT model - Dobby : Model
10
 
11
  This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
12
 
13
  **Example usage**:
14
- - For text only LLMs: `./llama.cpp/llama-cli -hf IQSeC-Lab/unsloth_llama_fine-tuned_model --jinja`
15
- - For multimodal models: `./llama.cpp/llama-mtmd-cli -hf IQSeC-Lab/unsloth_llama_fine-tuned_model --jinja`
16
 
17
  ## Available Model files:
18
- - `llama-3-8b-instruct.Q8_0.gguf`
19
 
20
  ## Ollama
21
  An Ollama Modelfile is included for easy deployment.
22
-
23
- ## Note
24
- The model's BOS token behavior was adjusted for GGUF compatibility.
25
  This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
26
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
3
  - gguf
4
  - llama.cpp
5
  - unsloth
6
+
7
  ---
8
 
9
+ # unsloth_llama_fine-tuned_model : GGUF
10
 
11
  This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
12
 
13
  **Example usage**:
14
+ - For text only LLMs: `llama-cli -hf vixxnyx/unsloth_llama_fine-tuned_model --jinja`
15
+ - For multimodal models: `llama-mtmd-cli -hf vixxnyx/unsloth_llama_fine-tuned_model --jinja`
16
 
17
  ## Available Model files:
18
+ - `llama-3-8b-Instruct.Q8_0.gguf`
19
 
20
  ## Ollama
21
  An Ollama Modelfile is included for easy deployment.
 
 
 
22
  This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
23
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
config.json CHANGED
@@ -1,30 +1,33 @@
1
  {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
- "torch_dtype": "float16",
9
- "eos_token_id": 128009,
10
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 4096,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 14336,
15
- "max_position_embeddings": 8192,
16
- "mlp_bias": false,
17
- "model_type": "llama",
18
- "num_attention_heads": 32,
19
- "num_hidden_layers": 32,
20
- "num_key_value_heads": 8,
21
- "pad_token_id": 128255,
22
- "pretraining_tp": 1,
23
- "rms_norm_eps": 1e-05,
24
- "rope_scaling": null,
25
  "rope_theta": 500000.0,
26
- "tie_word_embeddings": false,
27
- "unsloth_version": "2026.2.1",
28
- "use_cache": true,
29
- "vocab_size": 128256
30
- }
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128255,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_parameters": {
25
  "rope_theta": 500000.0,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": false,
29
+ "transformers_version": "5.5.0",
30
+ "unsloth_version": "2026.5.2",
31
+ "use_cache": true,
32
+ "vocab_size": 128256
33
+ }
llama-3-8b-instruct.Q8_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5320123365e6566ac3b46a2970723eda35790dcd200e3d97b451b551babf2031
3
- size 8540771104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ab7353da893d235371b7d0ab3af4d6d93f84ba69dc148e1a92621ba3c7d060
3
+ size 8540771136
llama-3-8b.Q8_0.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aafccfe69ff90f7d05ea8de705a80c6da570d571d0c5488a603866e6addb007e
3
- size 8540771584