MaziyarPanahi
commited on
Commit
•
4490293
1
Parent(s):
e597d9c
Update README.md
Browse files
README.md
CHANGED
@@ -16,14 +16,14 @@ inference: false
|
|
16 |
model_creator: MaziyarPanahi
|
17 |
quantized_by: MaziyarPanahi
|
18 |
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
19 |
-
model_name: calme-2.
|
20 |
datasets:
|
21 |
- MaziyarPanahi/legalkit_cot_reasoning_nous_hermes
|
22 |
---
|
23 |
|
24 |
<img src="./calme-2-legalkit.webp" alt="Calme-2 Models" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
25 |
|
26 |
-
# MaziyarPanahi/calme-2.
|
27 |
|
28 |
This model is an advanced iteration of the powerful `meta-llama/Meta-Llama-3.1-8B-Instruct`, specifically fine-tuned to enhance its capabilities in the legal domain. The fine-tuning process utilized a synthetically generated dataset derived from the French [LegalKit](https://huggingface.co/datasets/louisbrulenaudet/legalkit), a comprehensive legal language resource.
|
29 |
|
@@ -34,7 +34,7 @@ The resulting model combines the robust foundation of `Llama-3.1-8B` with tailor
|
|
34 |
|
35 |
# ⚡ Quantized GGUF
|
36 |
|
37 |
-
All GGUF models are available here: [MaziyarPanahi/calme-2.
|
38 |
|
39 |
|
40 |
# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
@@ -138,7 +138,7 @@ from transformers import pipeline
|
|
138 |
messages = [
|
139 |
{"role": "user", "content": "Who are you?"},
|
140 |
]
|
141 |
-
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-2.
|
142 |
pipe(messages)
|
143 |
|
144 |
|
@@ -146,8 +146,8 @@ pipe(messages)
|
|
146 |
|
147 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
148 |
|
149 |
-
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.
|
150 |
-
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.
|
151 |
```
|
152 |
|
153 |
|
|
|
16 |
model_creator: MaziyarPanahi
|
17 |
quantized_by: MaziyarPanahi
|
18 |
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
19 |
+
model_name: calme-2.3-legalkit-8b
|
20 |
datasets:
|
21 |
- MaziyarPanahi/legalkit_cot_reasoning_nous_hermes
|
22 |
---
|
23 |
|
24 |
<img src="./calme-2-legalkit.webp" alt="Calme-2 Models" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
25 |
|
26 |
+
# MaziyarPanahi/calme-2.3-legalkit-8b
|
27 |
|
28 |
This model is an advanced iteration of the powerful `meta-llama/Meta-Llama-3.1-8B-Instruct`, specifically fine-tuned to enhance its capabilities in the legal domain. The fine-tuning process utilized a synthetically generated dataset derived from the French [LegalKit](https://huggingface.co/datasets/louisbrulenaudet/legalkit), a comprehensive legal language resource.
|
29 |
|
|
|
34 |
|
35 |
# ⚡ Quantized GGUF
|
36 |
|
37 |
+
All GGUF models are available here: [MaziyarPanahi/calme-2.3-legalkit-8b-GGUF](https://huggingface.co/MaziyarPanahi/calme-2.3-legalkit-8b-GGUF)
|
38 |
|
39 |
|
40 |
# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
|
138 |
messages = [
|
139 |
{"role": "user", "content": "Who are you?"},
|
140 |
]
|
141 |
+
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-2.3-legalkit-8b")
|
142 |
pipe(messages)
|
143 |
|
144 |
|
|
|
146 |
|
147 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
148 |
|
149 |
+
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.3-legalkit-8b")
|
150 |
+
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.3-legalkit-8b")
|
151 |
```
|
152 |
|
153 |
|